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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    r
    1.31
    ид
    1.30
    imiento
    1.29
    𝚛
    1.27
    pval
    1.26
    lying
    1.24
    rj
    1.24
    ঞ্চি
    1.23
    Communic
    1.22
    n
    1.21
    POSITIVE LOGITS
    й
    2.27
    ल
    1.52
    場合に
    1.49
    ிறது
    1.46
    йки
    1.43
    र
    1.40
     vagas
    1.34
     volna
    1.28
    y
    1.27
    ה
    1.27
    Act Density 0.018%

    No Known Activations