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

    Neuronpedia

    INDEX
    Explanations

    Every

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Stay
    -0.06
     ایشان
    -0.06
    ede
    -0.06
    FY
    -0.06
    _ctl
    -0.06
    parency
    -0.06
    etag
    -0.06
    ме
    -0.06
    IDX
    -0.06
     mar
    -0.06
    POSITIVE LOGITS
     conosc
    0.07
    netinet
    0.07
     заним
    0.07
     compreh
    0.07
    不会
    0.07
    }'.
    0.07
    杀
    0.06
     Unsigned
    0.06
    Should
    0.06
    straints
    0.06
    Act Density 0.000%

    No Known Activations