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

    Neuronpedia

    INDEX
    Explanations

    resources and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    divide
    0.80
    engen
    0.79
    uning
    0.76
     কতটা
    0.75
     elég
    0.74
     apopt
    0.73
     menggambarkan
    0.71
     menjelaskan
    0.71
    럽
    0.71
     Psychologist
    0.70
    POSITIVE LOGITS
    žel
    0.62
     शेख
    0.59
    ឧបករណ៍
    0.58
    ṣ
    0.58
    द्र
    0.58
     Charge
    0.57
     treat
    0.57
    }^{*}\
    0.57
     traiter
    0.57
     szüks
    0.56
    Act Density 0.052%

    No Known Activations