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

    Neuronpedia

    INDEX
    Explanations

    code/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Spoj
    -0.07
     prim
    -0.07
    _OD
    -0.07
    orneys
    -0.07
     �
    -0.06
     нужно
    -0.06
    vi
    -0.06
     Рад
    -0.06
     caso
    -0.06
     KH
    -0.06
    POSITIVE LOGITS
     percentile
    0.07
    ALLERY
    0.06
    warehouse
    0.06
    rophe
    0.06
     dejting
    0.06
    ICK
    0.06
    nova
    0.06
    CEEDED
    0.06
    фер
    0.06
    UNICATION
    0.06
    Act Density 0.000%

    No Known Activations