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

    Neuronpedia

    INDEX
    Explanations

    say hard-to-interpret token

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     !=
    -0.09
    !=
    -0.09
    !='
    -0.08
    twitter
    -0.08
    gezogen
    -0.08
    _BOOL
    -0.08
     ineff
    -0.07
    NAME
    -0.07
    ->_
    -0.07
    sport
    -0.07
    POSITIVE LOGITS
     conjunto
    0.08
     primaria
    0.08
    positories
    0.08
    iconduct
    0.08
     atque
    0.08
     Première
    0.08
    Filtro
    0.08
     lm
    0.08
     gallons
    0.07
     ahorro
    0.07
    Act Density 0.000%

    No Known Activations