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

    Neuronpedia

    INDEX
    Explanations

    interstitial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    160
    -0.06
    .cursor
    -0.06
     Jahr
    -0.06
     evt
    -0.06
    _assoc
    -0.06
     readme
    -0.06
    Dragging
    -0.06
     hashlib
    -0.06
     Moms
    -0.06
    /ex
    -0.06
    POSITIVE LOGITS
    “我
    0.07
    mmm
    0.07
    ब
    0.07
    土
    0.06
     وص
    0.06
    ؤول
    0.06
     última
    0.06
    .jd
    0.06
    _else
    0.06
    lus
    0.06
    Act Density 0.006%

    No Known Activations