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

    Neuronpedia

    INDEX
    Explanations

    legal or specific topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ada
    0.88
    OP
    0.85
    arming
    0.79
    <0x8C>
    0.77
    idet
    0.77
    ará
    0.77
    ified
    0.76
    IA
    0.75
    arms
    0.75
    nder
    0.74
    POSITIVE LOGITS
    डून
    0.91
    纷
    0.85
     soirée
    0.82
    શન
    0.80
    ImageQueue
    0.78
     tôt
    0.75
     striées
    0.74
     incroy
    0.74
    ریان
    0.74
    শ
    0.74
    Act Density 0.000%

    No Known Activations