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

    Neuronpedia

    INDEX
    Explanations

    non-English characters and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    esquerda
    0.46
    ógł
    0.45
    ंदे
    0.45
     gestire
    0.45
     setae
    0.44
    äng
    0.43
    ئے
    0.42
    getCode
    0.42
    된
    0.42
    προ
    0.42
    POSITIVE LOGITS
    。
    0.45
    -
    0.44
    名称
    0.43
    ஹ
    0.43
    మ్
    0.38
    )
    0.38
     имени
    0.38
     именем
    0.38
     அந்த
    0.37
    事
    0.37
    Act Density 0.036%

    No Known Activations