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

    Neuronpedia

    INDEX
    Explanations

    driving

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     receiving
    -0.08
     submits
    -0.06
     customer
    -0.06
    你们
    -0.06
     файл
    -0.06
     debate
    -0.06
    ière
    -0.06
    est
    -0.06
    .DEBUG
    -0.06
    ....↵
    -0.06
    POSITIVE LOGITS
     спря
    0.07
     ngang
    0.07
     �
    0.07
     บร
    0.07
    �
    0.06
     ilma
    0.06
    _REV
    0.06
     Drawable
    0.06
    Compression
    0.06
    ¦
    0.06
    Act Density 0.005%

    No Known Activations