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

    Neuronpedia

    INDEX
    Explanations

    usually

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     usually
    -2.30
     Usually
    -2.19
    Usually
    -2.17
    usually
    -2.11
     normally
    -1.88
     biasanya
    -1.70
     normalerweise
    -1.67
     normalmente
    -1.66
    normally
    -1.64
    Normally
    -1.63
    POSITIVE LOGITS
    WebElementEntity
    0.77
    thias
    0.63
     Jacobsen
    0.56
     disambiguazione
    0.54
     anticipate
    0.53
     forthcoming
    0.53
    CLUSIVE
    0.53
     Италијани
    0.53
    љено
    0.53
    acebook
    0.51
    Act Density 0.084%

    No Known Activations