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

    Neuronpedia

    INDEX
    Explanations

    rape and sexual abuse seeking help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Gior
    0.46
     Gerardo
    0.45
    ികൾ
    0.45
    ிகள்
    0.43
    ികള്‍
    0.41
     geometría
    0.41
    Wes
    0.39
    Georges
    0.39
    愘
    0.39
     Azores
    0.38
    POSITIVE LOGITS
     rape
    0.52
    cpp
    0.51
    rape
    0.47
     CPP
    0.46
     SCP
    0.45
     raped
    0.45
    CPP
    0.44
    MH
    0.42
     दुष्
    0.42
    MCP
    0.41
    Act Density 0.009%

    No Known Activations