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

    Neuronpedia

    INDEX
    Explanations

    win

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     اینکه
    -0.07
    dots
    -0.07
    -mon
    -0.07
    experience
    -0.06
    мотр
    -0.06
    _[
    -0.06
    UPDATE
    -0.06
     jMenuItem
    -0.06
     genome
    -0.06
    敵
    -0.06
    POSITIVE LOGITS
     NON
    0.06
     depressing
    0.06
     Gloria
    0.06
    laş
    0.06
     explodes
    0.06
     sympathy
    0.06
     SSD
    0.06
     MAG
    0.06
     DAM
    0.06
     neměl
    0.06
    Act Density 0.008%

    No Known Activations