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

    Neuronpedia

    INDEX
    Explanations

    teachings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zonder
    -0.07
     AFP
    -0.07
     Lack
    -0.06
    平方
    -0.06
    Exclusive
    -0.06
     Wert
    -0.06
     Shirt
    -0.06
    ares
    -0.06
    ประกาศ
    -0.06
     Dagger
    -0.06
    POSITIVE LOGITS
     Msg
    0.07
    ).
↵
    0.06
    _title
    0.06
    Formatter
    0.06
     surgeon
    0.06
    .zero
    0.06
    ẳng
    0.06
    抵
    0.06
     rotor
    0.06
    �i
    0.06
    Act Density 0.040%

    No Known Activations