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

    Neuronpedia

    INDEX
    Explanations

    Hebrew

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     داش
    -0.08
    Imp
    -0.07
     Instit
    -0.07
    _STAT
    -0.07
    (actions
    -0.06
     mice
    -0.06
    tiler
    -0.06
     arsen
    -0.06
     lasc
    -0.06
    ustum
    -0.06
    POSITIVE LOGITS
     Hebrew
    0.16
    brew
    0.09
     Heb
    0.08
     heb
    0.07
     Rebecca
    0.07
     Heather
    0.07
    October
    0.07
     Exodus
    0.07
     reverence
    0.06
     Contributors
    0.06
    Act Density 0.001%

    No Known Activations