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

    Neuronpedia

    INDEX
    Explanations

    -term

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     тор
    -0.07
     such
    -0.07
    .No
    -0.07
     debated
    -0.06
     ein
    -0.06
    arry
    -0.06
     země
    -0.06
     neutrality
    -0.06
     definition
    -0.06
     Thursday
    -0.06
    POSITIVE LOGITS
     longtime
    0.08
    -term
    0.07
    TER
    0.07
    方向
    0.07
    RCT
    0.07
     problém
    0.06
    season
    0.06
     TP
    0.06
    _FWD
    0.06
     Brain
    0.06
    Act Density 0.038%

    No Known Activations