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

    Neuronpedia

    INDEX
    Explanations

    patterns and structures in hierarchical data representations

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

    identifiers found in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    photobucket
    -0.33
    GOTREF
    -0.33
     Perusahaan
    -0.31
     cualquiera
    -0.31
     ostavi
    -0.31
    jména
    -0.31
     vych
    -0.30
     např
    -0.30
    tidak
    -0.30
     betrekking
    -0.30
    POSITIVE LOGITS
    protoimpl
    0.59
    RegressionTest
    0.58
    <unused28>
    0.55
    <unused41>
    0.55
    <unused16>
    0.55
    <unused8>
    0.55
    <unused52>
    0.54
    <unused74>
    0.54
    <unused47>
    0.54
    <unused14>
    0.54
    Act Density 0.005%

    No Known Activations