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

    Neuronpedia

    INDEX
    Explanations

    role in or involvement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ర్చు
    0.71
     pertenec
    0.70
    Benzoimidazole
    0.68
    インテリア
    0.67
     Udemy
    0.67
    Interfaz
    0.67
    reqParams
    0.66
    onnés
    0.66
    TreeWidgetItem
    0.66
    Diethyl
    0.66
    POSITIVE LOGITS
    ในการ
    1.34
    ក្នុងការ
    1.06
     in
    0.92
    กับการ
    0.92
     involved
    0.86
     facilitating
    0.85
     alongside
    0.81
     factor
    0.79
     during
    0.77
    facilit
    0.76
    Act Density 0.191%

    No Known Activations