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

    Neuronpedia

    INDEX
    Explanations

    history

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    во
    -0.08
     إنه
    -0.07
     Ana
    -0.07
    💤
    -0.06
     Bacon
    -0.06
     VW
    -0.06
    멍
    -0.06
     ow
    -0.06
    嘴角
    -0.06
    马丁
    -0.06
    POSITIVE LOGITS
    دولة
    0.07
    Styles
    0.07
     plus
    0.07
     bied
    0.07
    .menuStrip
    0.07
    blade
    0.07
    _Public
    0.07
     elite
    0.07
    \Database
    0.07
     Lee
    0.07
    Act Density 0.007%

    No Known Activations