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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Evento
    -0.07
     título
    -0.07
    14
    -0.06
     polis
    -0.06
    loyd
    -0.06
    22
    -0.06
     verify
    -0.06
    :
    -0.06
    rush
    -0.06
    ته
    -0.06
    POSITIVE LOGITS
    .int
    0.07
     comforting
    0.07
     Flat
    0.07
     sonucu
    0.06
    _PAY
    0.06
    BitConverter
    0.06
    .spatial
    0.06
     باع
    0.06
     screams
    0.06
     inds
    0.06
    Act Density 0.003%

    No Known Activations