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

    Neuronpedia

    INDEX
    Explanations

    starting with the need for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +
    0.50
    その他の
    0.44
    [
    0.43
    決して
    0.41
    7
    0.41
    9
    0.41
    -
    0.41
    0
    0.41
    或其他
    0.40
    /
    0.40
    POSITIVE LOGITS
    我們先
    1.05
     먼저
    0.82
    我們要
    0.79
     precisamos
    0.79
    我们需要
    0.77
     basics
    0.77
     necesitamos
    0.77
     başlayalım
    0.76
    我们要
    0.75
    まず
    0.74
    Act Density 0.036%

    No Known Activations