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

    Neuronpedia

    INDEX
    Explanations

    sexual assault

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Som
    0.42
    ouml
    0.40
    Radius
    0.39
    El
    0.37
     রায়
    0.37
    瑞
    0.37
    Ray
    0.36
    avaju
    0.35
    ڡ
    0.35
    ZM
    0.35
    POSITIVE LOGITS
     Assault
    0.67
     assault
    0.58
     assaulting
    0.50
     assaults
    0.47
     assaulted
    0.46
    ASS
    0.44
    adid
    0.43
     ass
    0.43
     ASS
    0.43
     Assertion
    0.42
    Act Density 0.009%

    No Known Activations