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

    Neuronpedia

    INDEX
    Explanations

    a practiced, a deliberate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !!”
    0.93
     tzv
    0.91
    !!"
    0.90
     tzw
    0.89
     môžu
    0.87
    !!
    0.86
    !";
    0.86
     emberek
    0.84
    可能会
    0.84
     môže
    0.84
    POSITIVE LOGITS
     grotes
    0.78
     tincture
    0.76
     disconcert
    0.76
     phleg
    0.74
     palpable
    0.71
     osmotic
    0.70
     mottled
    0.69
     prophylaxis
    0.68
     diminution
    0.68
     osmosis
    0.68
    Act Density 0.335%

    No Known Activations