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

    Neuronpedia

    INDEX
    Explanations

    np.random.rand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Riv
    0.73
    Sc
    0.65
    Screw
    0.65
    }}.
    0.64
    ሏ
    0.62
    Continued
    0.62
    Ent
    0.61
    Est
    0.60
    Primitive
    0.60
     conscious
    0.58
    POSITIVE LOGITS
    ilov
    0.95
    >≤</
    0.91
    ﺧ
    0.91
     tiế
    0.89
    殯
    0.89
    ת
    0.89
     covenant
    0.88
     stopwatch
    0.87
     fadeInUp
    0.87
     sos
    0.85
    Act Density 0.037%

    No Known Activations