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

    Neuronpedia

    INDEX
    Explanations

    women

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cuis
    -0.06
     intends
    -0.06
     load
    -0.06
     Wendy
    -0.06
    .setSize
    -0.06
    NumberFormatException
    -0.06
     couch
    -0.06
     lesbians
    -0.06
     mask
    -0.06
     nov
    -0.06
    POSITIVE LOGITS
     електрон
    0.07
     QUICK
    0.07
    ्बन
    0.07
    ัณฑ
    0.06
     nerv
    0.06
    ?;↵
    0.06
     thân
    0.06
    ASSES
    0.06
    _marshaled
    0.06
     Cemetery
    0.06
    Act Density 0.134%

    No Known Activations