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

    Neuronpedia

    INDEX
    Explanations

    Inappropriate touching/sexual assault

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     پدر
    -0.07
    Persons
    -0.06
    Thai
    -0.06
     ambitions
    -0.06
    Print
    -0.06
     سنوات
    -0.06
    .skills
    -0.06
     Sadly
    -0.06
     سنة
    -0.06
    CUR
    -0.06
    POSITIVE LOGITS
    止
    0.07
     oxide
    0.07
     ruled
    0.06
     음
    0.06
     açı
    0.06
    icie
    0.06
     tul
    0.06
    .solution
    0.06
    zman
    0.06
     FIG
    0.06
    Act Density 0.018%

    No Known Activations