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

    Neuronpedia

    INDEX
    Explanations

    US or marital disagreement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    度
    0.87
    效
    0.82
    linspace
    0.78
    зик
    0.75
    哫
    0.73
    Degree
    0.73
    China
    0.72
    椑
    0.72
    🍪
    0.71
    }^{*}(\
    0.70
    POSITIVE LOGITS
     tout
    0.81
     עוד
    0.75
    ვილი
    0.73
     প্রদর্শন
    0.71
    ussa
    0.71
     metabolic
    0.71
    隴
    0.69
     trailer
    0.68
    i
    0.68
     AppComponent
    0.67
    Act Density 0.000%

    No Known Activations