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

    Neuronpedia

    INDEX
    Explanations

    mu

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     прок
    -0.07
    _pdf
    -0.06
     программ
    -0.06
    ######↵
    -0.06
    LAST
    -0.06
     ين
    -0.06
     Гар
    -0.06
     ax
    -0.06
    housing
    -0.06
     squid
    -0.06
    POSITIVE LOGITS
    备份
    0.07
    <::
    0.07
    578
    0.06
     metrics
    0.06
    üny
    0.06
    _starts
    0.06
     điển
    0.06
    _anchor
    0.06
     takdir
    0.06
    避
    0.06
    Act Density 0.000%

    No Known Activations