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

    Neuronpedia

    INDEX
    Explanations

    links to external resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ar
    0.81
    ah
    0.80
    ofinstagram
    0.78
    ov
    0.73
     TCE
    0.72
    od
    0.68
    ia
    0.68
    at
    0.66
    orus
    0.66
    для
    0.66
    POSITIVE LOGITS
    ម្បី
    0.80
    𝘳
    0.80
    ﺏ
    0.77
    𝘭
    0.76
    0.75
    gunaan
    0.74
    ၍
    0.74
    ル
    0.73
    ेक्स
    0.72
    नहीं
    0.72
    Act Density 0.003%

    No Known Activations