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

    Neuronpedia

    INDEX
    Explanations

    breasts/chest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     betting
    -0.08
     regulators
    -0.08
     fabrication
    -0.07
     App
    -0.07
     ro
    -0.07
    ísticas
    -0.06
     MAG
    -0.06
    gos
    -0.06
     Te
    -0.06
    entes
    -0.06
    POSITIVE LOGITS
     Pods
    0.07
    ...)
    0.06
    "<<
    0.06
     potrze
    0.06
     dictionaryWith
    0.06
    Poster
    0.06
    ')['
    0.06
    ()._
    0.06
     discomfort
    0.06
    _"+
    0.06
    Act Density 0.011%

    No Known Activations