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

    Neuronpedia

    INDEX
    Explanations

    Overhearing/observing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Achievement
    -0.08
    YRO
    -0.07
     typical
    -0.06
    び
    -0.06
     corrected
    -0.06
     panties
    -0.06
    903
    -0.06
     Dalton
    -0.06
     Jer
    -0.06
    _Buffer
    -0.06
    POSITIVE LOGITS
    urry
    0.07
     divis
    0.06
    Picture
    0.06
     göl
    0.06
    sPid
    0.06
    deme
    0.06
     {{↵
    0.06
     OUR
    0.06
    ея
    0.06
    /db
    0.06
    Act Density 0.044%

    No Known Activations