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

    Neuronpedia

    INDEX
    Explanations

    using

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autopsy
    -0.07
    (Component
    -0.07
     absorption
    -0.07
     exposures
    -0.07
     insisting
    -0.07
    Voice
    -0.07
     transition
    -0.07
     denial
    -0.07
     affirmed
    -0.06
     Ні
    -0.06
    POSITIVE LOGITS
     pornofilm
    0.08
    ohl
    0.07
     efekt
    0.06
    ，並
    0.06
    rule
    0.06
     semiclass
    0.06
    ে
    0.06
    LENGTH
    0.06
    rolley
    0.06
    _datasets
    0.06
    Act Density 0.011%

    No Known Activations