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

    Neuronpedia

    INDEX
    Explanations

    Plutonium and nuclear materials

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hag
    -0.08
     Nag
    -0.07
    Swap
    -0.07
     skinny
    -0.07
    agged
    -0.06
    addle
    -0.06
    _p
    -0.06
    eten
    -0.06
    /:
    -0.06
     observation
    -0.06
    POSITIVE LOGITS
     cresc
    0.06
    -int
    0.06
    ORITY
    0.06
    सल
    0.06
    ICON
    0.06
     IPCC
    0.06
    震
    0.06
    .integer
    0.06
    _COLUMNS
    0.06
     siêu
    0.06
    Act Density 0.001%

    No Known Activations