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

    Neuronpedia

    INDEX
    Explanations

    decision

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sam
    -0.07
    ('${
    -0.07
     gag
    -0.07
     Gupta
    -0.06
     Granny
    -0.06
    _HOLD
    -0.06
     compost
    -0.06
    .rawQuery
    -0.06
    np
    -0.06
    .WRAP
    -0.06
    POSITIVE LOGITS
     decision
    0.08
     decisions
    0.08
    charger
    0.07
    ija
    0.07
     Picasso
    0.07
     điện
    0.07
     deton
    0.07
    最後
    0.07
     чемпіон
    0.07
    .Errors
    0.07
    Act Density 0.006%

    No Known Activations