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

    Neuronpedia

    INDEX
    Explanations

    al

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scale
    -0.07
     illness
    -0.07
    INCREMENT
    -0.06
     [...]
    -0.06
    一年
    -0.06
     tsunami
    -0.06
     kazanç
    -0.06
    战争
    -0.06
    attery
    -0.06
    ́
    -0.06
    POSITIVE LOGITS
     behavioral
    0.11
     Behavioral
    0.08
     baff
    0.07
     bif
    0.06
    -ranked
    0.06
     Dew
    0.06
    enef
    0.06
     behavioural
    0.06
     dismal
    0.06
     simpl
    0.06
    Act Density 0.004%

    No Known Activations