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

    Neuronpedia

    INDEX
    Explanations

    clear cache or if condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    In
    0.84
    Tooth
    0.79
    Vac
    0.79
    Bal
    0.79
    Diet
    0.78
    Pl
    0.77
    An
    0.76
    Pre
    0.76
    Per
    0.76
    E
    0.75
    POSITIVE LOGITS
     （
    0.75
     normal
    0.74
     id
    0.72
     closer
    0.71
     flash
    0.71
     space
    0.70
     innovative
    0.69
     momentum
    0.69
     tight
    0.68
     انتظار
    0.68
    Act Density 0.001%

    No Known Activations