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

    Neuronpedia

    INDEX
    Explanations

    ready to proceed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Maybe
    1.06
     Maybe
    0.92
    maybe
    0.91
     maybe
    0.89
     might
    0.87
    Sometimes
    0.84
     misschien
    0.84
    If
    0.83
     if
    0.77
    might
    0.76
    POSITIVE LOGITS
     eager
    0.92
     poised
    0.85
    ready
    0.80
     eagerly
    0.78
     ready
    0.77
     कमर
    0.72
    骈
    0.71
     excited
    0.71
     anticipation
    0.70
     Readiness
    0.70
    Act Density 0.370%

    No Known Activations