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

    Neuronpedia

    INDEX
    Explanations

    females

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    successfully
    -0.07
     domic
    -0.06
     burden
    -0.06
    Every
    -0.06
    рож
    -0.06
     getInt
    -0.06
     προϊ
    -0.06
    ach
    -0.06
     مو
    -0.06
    meaning
    -0.06
    POSITIVE LOGITS
     Cleveland
    0.06
    feof
    0.06
     finals
    0.06
    .cols
    0.06
    們
    0.06
     cousin
    0.06
     Greenville
    0.06
    (router
    0.06
    andre
    0.06
     colorWithRed
    0.06
    Act Density 0.000%

    No Known Activations