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

    Neuronpedia

    INDEX
    Explanations

    Positive reviews/promotion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Compute
    -0.06
    SUM
    -0.06
     pals
    -0.06
    ราช
    -0.06
    _RANDOM
    -0.06
    plet
    -0.06
    iding
    -0.06
    .mContext
    -0.06
     SU
    -0.06
    CF
    -0.06
    POSITIVE LOGITS
     عق
    0.07
    (newState
    0.07
    ??
    0.06
     pimp
    0.06
     insight
    0.06
     slo
    0.06
     specializing
    0.06
    -transfer
    0.06
     withhold
    0.06
     право
    0.06
    Act Density 0.041%

    No Known Activations