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

    Neuronpedia

    INDEX
    Explanations

    quality evaluation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    377
    -0.07
     drinking
    -0.07
    Longitude
    -0.07
    IGHT
    -0.06
    插
    -0.06
    };
    -0.06
    ;\
    -0.06
    Rx
    -0.06
    chemy
    -0.06
    617
    -0.06
    POSITIVE LOGITS
    ecess
    0.08
    пон
    0.07
     základ
    0.07
     approximately
    0.07
     Dul
    0.06
     Uttar
    0.06
     BDSM
    0.06
    _deleted
    0.06
     Gregg
    0.06
     مشکلات
    0.06
    Act Density 0.014%

    No Known Activations