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

    Neuronpedia

    INDEX
    Explanations

    game titles and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    D
    0.77
     the
    0.76
    0.71
    S
    0.68
     A
    0.65
     D
    0.63
    T
    0.62
    M
    0.62
    E
    0.60
     M
    0.60
    POSITIVE LOGITS
    čio
    0.79
     suffices
    0.78
     announces
    0.77
     sAlarm
    0.73
     strives
    0.70
     advises
    0.69
    adə
    0.69
     змо
    0.69
     awaits
    0.69
     izango
    0.68
    Act Density 2.171%

    No Known Activations