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

    Neuronpedia

    INDEX
    Explanations

    say speaking verbs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quits
    -0.07
     іс
    -0.07
    ใหญ
    -0.07
     Seller
    -0.06
    sein
    -0.06
    FSIZE
    -0.06
     inlet
    -0.06
    )=(
    -0.06
    (c
    -0.06
     ноя
    -0.06
    POSITIVE LOGITS
     ago
    0.07
    -ons
    0.07
    费
    0.07
    їв
    0.07
     slightest
    0.06
    -native
    0.06
     consc
    0.06
    #aa
    0.06
    lington
    0.06
    _lang
    0.06
    Act Density 0.037%

    No Known Activations