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

    Neuronpedia

    INDEX
    Explanations

    optim after as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    paragraph
    0.37
    پیگنڈ
    0.36
    paragraphs
    0.35
    Paragraph
    0.34
    য়াছে
    0.31
     useCustom
    0.30
    ᕈ
    0.30
     párrafo
    0.30
    感想
    0.30
    صرية
    0.30
    POSITIVE LOGITS
    S
    0.34
     d
    0.30
     s
    0.28
     W
    0.27
     alb
    0.27
    D
    0.27
     w
    0.27
    0.27
    C
    0.27
    Q
    0.26
    Act Density 0.000%

    No Known Activations