Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    programming concepts related to data loading and serialization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Serialization/deserialization and data handling

    np_acts-logits-general · gemini-2.0-flash

    reconstruction and deserialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oprot
    -0.57
    EDEFAULT
    -0.56
     Wikimedijinoj
    -0.50
    CppMethod
    -0.47
    bcryptjs
    -0.46
    StructEnd
    -0.45
    OOTDTY
    -0.44
     gogh
    -0.42
    cèse
    -0.42
     vectorielles
    -0.42
    POSITIVE LOGITS
     rekon
    0.53
     reconstruct
    0.52
     reconstructed
    0.49
     restored
    0.48
     recovered
    0.45
     reconstru
    0.45
     reconstruction
    0.44
     Recon
    0.44
     recon
    0.43
    Recon
    0.43
    Act Density 0.530%

    No Known Activations