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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Random
    -0.07
     unix
    -0.06
     dass
    -0.06
    Ascii
    -0.06
    repair
    -0.06
    RTL
    -0.06
    ampp
    -0.06
    _m
    -0.06
     polyline
    -0.06
     Lage
    -0.06
    POSITIVE LOGITS
     vile
    0.07
     blackout
    0.07
     EAR
    0.07
     сама
    0.06
    _PKG
    0.06
     hành
    0.06
    Health
    0.06
     scholarly
    0.06
     kun
    0.06
    总
    0.06
    Act Density 0.061%

    No Known Activations