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

    Neuronpedia

    INDEX
    Explanations

    code documentation descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     islands
    0.91
    жмите
    0.81
     degenerate
    0.80
     Бо
    0.80
     А
    0.79
     lonely
    0.79
     hairy
    0.78
     pliers
    0.78
     groves
    0.78
     Ж
    0.77
    POSITIVE LOGITS
    わ
    0.77
    ant
    0.76
    start
    0.75
    uur
    0.74
    el
    0.70
    ung
    0.70
    #(
    0.70
    Ut
    0.70
    ze
    0.68
    ree
    0.67
    Act Density 0.054%

    No Known Activations