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

    Neuronpedia

    INDEX
    Explanations

    AM

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -lasting
    -0.08
    isbn
    -0.07
     racially
    -0.07
    antics
    -0.07
     unresolved
    -0.07
    再也不
    -0.07
     יהודי
    -0.07
    キャッシ
    -0.07
    ,private
    -0.07
    /ic
    -0.07
    POSITIVE LOGITS
     PCM
    0.09
    のある
    0.07
    _foot
    0.07
     CT
    0.07
    玉
    0.07
    (segment
    0.07
    𝕝
    0.07
     woman
    0.07
    _Mod
    0.07
     folding
    0.07
    Act Density 0.001%

    No Known Activations