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

    Neuronpedia

    INDEX
    Explanations

    terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فرزند
    -0.07
     Glad
    -0.06
     매매가
    -0.06
     قل
    -0.06
     lze
    -0.06
    brates
    -0.06
    _sl
    -0.06
     svůj
    -0.06
     hầu
    -0.06
     karşısında
    -0.06
    POSITIVE LOGITS
    ]='\
    0.07
    igner
    0.06
    Socket
    0.06
    reature
    0.06
    .gov
    0.06
     pcm
    0.06
     divorce
    0.06
     american
    0.06
    .readlines
    0.06
    人間
    0.06
    Act Density 0.001%

    No Known Activations