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

    Neuronpedia

    INDEX
    Explanations

    profanity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stray
    -0.07
    ترة
    -0.07
    يز
    -0.06
    یزی
    -0.06
    emez
    -0.06
    ик
    -0.06
    tracking
    -0.06
     Brooklyn
    -0.06
    Memory
    -0.06
    ยม
    -0.06
    POSITIVE LOGITS
     Apartments
    0.07
     hton
    0.06
     RTWF
    0.06
    (age
    0.06
    !(↵
    0.06
     Foto
    0.06
    <>();
↵
    0.06
    Priv
    0.06
    ,json
    0.06
     niên
    0.06
    Act Density 0.064%

    No Known Activations