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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adow
    -0.07
    textView
    -0.07
     reliant
    -0.06
    ancellation
    -0.06
     todas
    -0.06
    _VAR
    -0.06
     Judgment
    -0.06
     sounding
    -0.06
     đá
    -0.06
    iva
    -0.06
    POSITIVE LOGITS
    .writeObject
    0.07
     bước
    0.07
     благод
    0.06
     �
    0.06
    .FileName
    0.06
    .AutoComplete
    0.06
     Personnel
    0.06
    축
    0.06
     exercise
    0.06
    Confirmation
    0.06
    Act Density 0.001%

    No Known Activations