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

    Neuronpedia

    INDEX
    Explanations

    %

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     boosted
    -0.07
    75
    -0.06
     reopen
    -0.06
     언어
    -0.06
    _checker
    -0.06
     -->
    -0.06
    ζ
    -0.06
     intertwined
    -0.06
    联
    -0.06
     impr
    -0.06
    POSITIVE LOGITS
    .Persistent
    0.07
    الش
    0.07
    있
    0.06
    映画
    0.06
    askets
    0.06
    υκ
    0.06
     trot
    0.06
    орт
    0.06
    !')↵↵
    0.06
     unsere
    0.06
    Act Density 0.038%

    No Known Activations