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

    Neuronpedia

    INDEX
    Explanations

    variables and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ゃ
    -0.06
     ماد
    -0.06
    _mappings
    -0.06
    suppress
    -0.06
     dispositivo
    -0.06
    �
    -0.06
     Shuffle
    -0.06
    Transform
    -0.06
     Til
    -0.06
    _CHANNELS
    -0.06
    POSITIVE LOGITS
    +"</
    0.07
    .erb
    0.07
     PARTY
    0.06
     долж
    0.06
    -the
    0.06
     zast
    0.06
    
    0.06
    þ
    0.06
    quist
    0.06
     "}↵
    0.06
    Act Density 0.121%

    No Known Activations