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

    Neuronpedia

    INDEX
    Explanations

    resignation, readiness, criteria, safety, empirical quantile

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    T
    0.91
    F
    0.88
    A
    0.83
    u
    0.82
    D
    0.80
    L
    0.78
    i
    0.75
    s
    0.75
    C
    0.74
    ्स
    0.69
    POSITIVE LOGITS
     tumultuous
    0.97
     grapefruit
    0.91
     vows
    0.91
     luôn
    0.90
     intimidation
    0.89
    ೀವ
    0.88
     tyranny
    0.87
     grilling
    0.87
     rectal
    0.87
     Rodeo
    0.87
    Act Density 0.001%

    No Known Activations