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

    Neuronpedia

    INDEX
    Explanations

    Flat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Erro
    -0.07
    lucent
    -0.06
     caffeine
    -0.06
     Sat
    -0.06
     embarked
    -0.06
     album
    -0.06
     addict
    -0.06
    handled
    -0.06
    unken
    -0.06
     Sgt
    -0.06
    POSITIVE LOGITS
     '?
    0.07
    湿
    0.06
    097
    0.06
    千
    0.06
    486
    0.06
    ━�
    0.06
     �
    0.06
    ileged
    0.06
     Kis
    0.06
    ato
    0.06
    Act Density 0.000%

    No Known Activations