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

    Neuronpedia

    INDEX
    Explanations

    single digit numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ведь
    -0.07
     ('
    -0.07
    ojení
    -0.06
     cuc
    -0.06
    qus
    -0.06
    ilenames
    -0.06
     impeccable
    -0.06
     whereby
    -0.06
     comida
    -0.06
    elda
    -0.06
    POSITIVE LOGITS
    0
    0.07
     Максим
    0.07
    640
    0.07
     abrasive
    0.07
     Oil
    0.07
    १
    0.07
    _pushButton
    0.07
     λίγ
    0.07
    <Expression
    0.06
    珠
    0.06
    Act Density 0.047%

    No Known Activations