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

    Neuronpedia

    INDEX
    Explanations

    coding documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AN
    -0.06
    <Any
    -0.06
    '+
    -0.06
    flex
    -0.06
    %，
    -0.06
    инок
    -0.05
     Hazard
    -0.05
     Provid
    -0.05
    (web
    -0.05
    ريم
    -0.05
    POSITIVE LOGITS
     nền
    0.06
    .helper
    0.06
     nhanh
    0.06
     emotions
    0.06
    .netty
    0.06
     於
    0.06
    лоп
    0.06
    _friend
    0.06
     Legacy
    0.06
    .)
    0.06
    Act Density 0.017%

    No Known Activations