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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to crime, violence, and fear

    oai_token-act-pair · gemini-2.0-flash

    News, violence and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.70
    IsContent
    -0.52
    قایناقلار
    -0.51
     complètes
    -0.49
    setupUi
    -0.49
     esportivo
    -0.48
     aceea
    -0.47
     tissus
    -0.47
     paesi
    -0.47
    psum
    -0.46
    POSITIVE LOGITS
    InputTagHelper
    0.57
    مراجع
    0.55
    ApiModelProperty
    0.51
    ValueStyle
    0.50
    حوالہ
    0.50
    comuna
    0.50
     StatelessWidget
    0.50
    новниш
    0.50
    cobra
    0.49
    المراجع
    0.49
    Act Density 0.573%

    No Known Activations