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

    Neuronpedia

    INDEX
    Explanations

    scheduled events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    plot
    -0.07
    Navigator
    -0.07
     depress
    -0.07
    chnitt
    -0.07
    $arity
    -0.07
     svens
    -0.06
     इत
    -0.06
     Alley
    -0.06
     لي
    -0.06
    Qui
    -0.06
    POSITIVE LOGITS
    Pixels
    0.07
     Former
    0.06
    ظٹط
    0.06
     Multiple
    0.06
     대해
    0.06
    ську
    0.06
     dawn
    0.06
     Commun
    0.06
     Brotherhood
    0.06
    何
    0.06
    Act Density 0.011%

    No Known Activations