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

    Neuronpedia

    INDEX
    Explanations

    indicating where things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    を下
    0.50
    是我们
    0.46
    以下
    0.44
    Margin
    0.43
    నాన్ని
    0.42
     Workout
    0.41
    ηγ
    0.40
    PROTON
    0.40
    zczeg
    0.40
     Trident
    0.39
    POSITIVE LOGITS
    it
    0.57
    es
    0.57
    os
    0.46
     झूठ
    0.46
    rag
    0.45
     amiable
    0.45
    fig
    0.45
    false
    0.44
    at
    0.44
    ect
    0.44
    Act Density 0.003%

    No Known Activations