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

    Neuronpedia

    INDEX
    Explanations

    play or numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inductively
    0.94
     polite
    0.91
     impersonal
    0.84
     choose
    0.83
     Groups
    0.82
     adsorb
    0.79
     deviate
    0.79
     corrected
    0.78
     subgroups
    0.78
    ANEOUS
    0.78
    POSITIVE LOGITS
    플레이
    0.79
    9
    0.76
    8
    0.76
    1
    0.72
    play
    0.71
    Play
    0.71
    7
    0.70
    游客
    0.70
    3
    0.70
    2
    0.69
    Act Density 0.000%

    No Known Activations