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

    Neuronpedia

    INDEX
    Explanations

    mathematical indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     New
    0.54
    y
    0.53
     new
    0.52
     fate
    0.50
     I
    0.49
     John
    0.47
     Na
    0.46
    New
    0.45
     mist
    0.45
     Stephen
    0.45
    POSITIVE LOGITS
    )=
    0.77
    $_{
    0.77
    étrica
    0.77
    ϑ
    0.76
     ∈
    0.70
    ète
    0.69
    verage
    0.68
     คือ
    0.68
     denotes
    0.67
    ୪
    0.67
    Act Density 0.715%

    No Known Activations