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

    Neuronpedia

    INDEX
    Explanations

    research studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    !)
    -0.08
    帝国
    -0.07
    urger
    -0.06
    eds
    -0.06
    激素
    -0.06
    沙特
    -0.06
    爱尔
    -0.06
    聞いた
    -0.06
     '.')
    -0.06
    Fd
    -0.06
    POSITIVE LOGITS
    _personal
    0.08
    бри
    0.07
     CString
    0.07
    ycling
    0.07
    .copy
    0.07
     pointing
    0.07
     Supplementary
    0.07
     Stainless
    0.07
    ños
    0.07
     Compression
    0.07
    Act Density 0.021%

    No Known Activations