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

    Neuronpedia

    INDEX
    Explanations

    say ".Dec"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ively
    -0.07
     indefinitely
    -0.07
    leted
    -0.07
    Reference
    -0.06
    castle
    -0.06
    emente
    -0.06
    isoft
    -0.06
    ากร
    -0.06
    Processing
    -0.06
    buat
    -0.06
    POSITIVE LOGITS
     몰
    0.07
     COMMAND
    0.07
     东
    0.06
     모
    0.06
    adele
    0.06
    )","
    0.06
    LAG
    0.06
    .str
    0.06
     INS
    0.06
     درمان
    0.06
    Act Density 0.002%

    No Known Activations