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

    Neuronpedia

    INDEX
    Explanations

    items or concepts related to categorization or listing

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

    special characters followed by text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tjän
    -0.50
    ValueStyle
    -0.47
     ktorí
    -0.46
    Cyfeiriadau
    -0.45
    Referanser
    -0.45
    kově
    -0.42
     useAppContext
    -0.41
    AxisAlignment
    -0.41
     ustedes
    -0.40
    Viited
    -0.39
    POSITIVE LOGITS
     ujednoznacz
    0.52
    EndContext
    0.49
    Personendaten
    0.47
    0.42
     <>",
    0.42
    InjectAttribute
    0.41
    uxxxx
    0.41
     Distributions
    0.41
    rancy
    0.40
    ۜ
    0.40
    Act Density 0.239%

    No Known Activations