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

    Neuronpedia

    INDEX
    Explanations

    hub

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ">';
↵
    -0.06
     Stacy
    -0.06
     الأمر
    -0.06
    Separ
    -0.06
    _prefix
    -0.06
    (o
    -0.06
    _pickle
    -0.06
    .publisher
    -0.05
     pointless
    -0.05
    ystal
    -0.05
    POSITIVE LOGITS
    hum
    0.07
    -в
    0.06
    oleon
    0.06
    τώ
    0.06
    ิว
    0.06
    rats
    0.06
    minute
    0.06
     butterfly
    0.06
     gv
    0.06
     adjust
    0.06
    Act Density 0.000%

    No Known Activations