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

    Neuronpedia

    INDEX
    Explanations

    make instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Week
    -0.07
    nad
    -0.07
     invasive
    -0.07
    сок
    -0.06
    ayız
    -0.06
    _alarm
    -0.06
    occo
    -0.06
     implication
    -0.06
    itto
    -0.06
    _NOT
    -0.06
    POSITIVE LOGITS
     대전
    0.07
     xmlns
    0.07
    (models
    0.06
    marshaller
    0.06
     vstup
    0.06
    ObjectName
    0.06
    LayoutParams
    0.06
     Вар
    0.06
     dah
    0.06
     profitable
    0.06
    Act Density 0.005%

    No Known Activations