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

    Neuronpedia

    INDEX
    Explanations

    symbolic gestures and attempts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     رہتا
    0.82
     krijg
    0.80
     facts
    0.76
    baliknya
    0.76
     رہنے
    0.74
     WordPerfect
    0.72
     elenc
    0.72
     keyValue
    0.71
     joys
    0.71
    godic
    0.71
    POSITIVE LOGITS
     symbolic
    1.01
     attempt
    1.00
    Symbol
    0.91
     Symbolic
    0.87
     Attempt
    0.84
    Attempt
    0.82
     symbolically
    0.80
     attempts
    0.80
     homage
    0.79
     tribute
    0.76
    Act Density 0.377%

    No Known Activations