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

    Neuronpedia

    INDEX
    Explanations

    addresses or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aj
    0.79
     rec
    0.76
     dico
    0.76
    ৌম
    0.75
    iv
    0.74
     solide
    0.74
     intensely
    0.72
     explosion
    0.72
    em
    0.71
     Pyongyang
    0.71
    POSITIVE LOGITS
     Какой
    0.83
    щими
    0.81
    чая
    0.78
    ствует
    0.77
     eus
    0.75
    ษา
    0.74
     acuer
    0.73
     מד
    0.73
     многочис
    0.72
    ،
    0.72
    Act Density 0.000%

    No Known Activations