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

    Neuronpedia

    INDEX
    Explanations

    sexually suggestive prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ట్టిన
    0.44
     "'.$
    0.37
    ัญหา
    0.36
    🫰
    0.36
    सायिक
    0.35
    jillo
    0.35
    یشن
    0.34
     '.$
    0.33
    currentGame
    0.33
     مقرر
    0.32
    POSITIVE LOGITS
    s
    0.41
    pt
    0.39
     choose
    0.38
     We
    0.37
    Good
    0.37
    H
    0.36
    He
    0.36
    Choosing
    0.36
     Choose
    0.36
    Ay
    0.36
    Act Density 0.000%

    No Known Activations