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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PP
    -0.07
    就
    -0.06
     особи
    -0.06
     Stem
    -0.06
     jag
    -0.06
     leans
    -0.06
    pectrum
    -0.06
    piler
    -0.06
    消
    -0.06
    pp
    -0.06
    POSITIVE LOGITS
    živ
    0.08
    laws
    0.07
    REFER
    0.07
    mé
    0.07
    _Query
    0.06
    leading
    0.06
     efekt
    0.06
    PHP
    0.06
     excelente
    0.06
    ertainment
    0.06
    Act Density 0.105%

    No Known Activations