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

    Neuronpedia

    INDEX
    Explanations

    "Es" followed by Spanish text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    1.07
    ofinstagram
    0.96
    ה
    0.96
    ಯ
    0.96
     philanthropy
    0.91
     evade
    0.86
    sman
    0.84
     grudge
    0.82
    いる
    0.81
    𝐢
    0.81
    POSITIVE LOGITS
    itare
    0.89
     bombarded
    0.88
    ince
    0.83
    жено
    0.83
    एस
    0.80
    हों
    0.79
    冏
    0.79
    ২৮
    0.78
     spelled
    0.78
    hler
    0.78
    Act Density 0.006%

    No Known Activations