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

    Neuronpedia

    INDEX
    Explanations

    form of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     destinés
    0.77
    观念
    0.76
    مكان
    0.74
     திட்டம்
    0.71
     بشأن
    0.71
     전망
    0.71
    玩意
    0.70
     궁금
    0.69
    的可能性
    0.69
     destiné
    0.68
    POSITIVE LOGITS
     technically
    0.98
     equivalent
    0.95
     Technically
    0.94
     indire
    0.93
     indirect
    0.90
     Form
    0.87
    一種
    0.86
     forms
    0.85
    प्रकारे
    0.83
    Forms
    0.82
    Act Density 0.157%

    No Known Activations