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

    Neuronpedia

    INDEX
    Explanations

    original

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     any
    0.77
     dumping
    0.74
     determined
    0.74
     embroiled
    0.71
     होती
    0.70
     Immediately
    0.67
     कोण
    0.66
     moments
    0.65
     antibodies
    0.64
     rounding
    0.64
    POSITIVE LOGITS
    original
    1.03
     original
    1.02
    Original
    0.93
     Original
    0.90
     originals
    0.89
     originales
    0.88
    原来的
    0.85
    orig
    0.81
     ORIGINAL
    0.78
     ursprüng
    0.77
    Act Density 0.000%

    No Known Activations