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

    Neuronpedia

    INDEX
    Explanations

    financial forward-looking statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Delivery
    -0.07
    Fallback
    -0.07
    陸
    -0.07
    无力
    -0.07
    抱歉
    -0.07
    ники
    -0.07
     Ich
    -0.07
     vai
    -0.07
     doch
    -0.07
    ch
    -0.06
    POSITIVE LOGITS
     Pure
    0.07
     >>
    0.07
     dirs
    0.07
     e
    0.07
    esium
    0.06
    数目
    0.06
    leaflet
    0.06
     blaze
    0.06
     EXTRA
    0.06
    _proba
    0.06
    Act Density 0.002%

    No Known Activations