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

    Neuronpedia

    INDEX
    Explanations

    crisis and helplines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kraków
    0.71
    Profit
    0.71
    Telefono
    0.70
    Xiv
    0.69
    PopupWindow
    0.69
     telef
    0.69
    ífer
    0.69
    Amen
    0.69
    FRINGEMENT
    0.68
    icultura
    0.68
    POSITIVE LOGITS
     Knox
    0.75
     Contra
    0.75
     Metro
    0.74
     হত্যা
    0.72
     округа
    0.71
    全市
    0.67
     Community
    0.67
     Williamson
    0.65
    撞
    0.65
     Central
    0.65
    Act Density 0.044%

    No Known Activations