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

    Neuronpedia

    INDEX
    Explanations

    code or oder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oward
    -0.08
    砥
    -0.07
     ';
    -0.07
    odef
    -0.06
    ሥ
    -0.06
    _condition
    -0.06
    mtx
    -0.06
    ӊ
    -0.06
     proposition
    -0.06
    _written
    -0.06
    POSITIVE LOGITS
    (numbers
    0.08
     Facilities
    0.07
     crashes
    0.07
    טרה
    0.07
     Autom
    0.07
     Пр
    0.07
    (cr
    0.07
    .Interface
    0.07
    經常
    0.07
     propiedad
    0.07
    Act Density 0.000%

    No Known Activations