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

    Neuronpedia

    INDEX
    Explanations

    your credential placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     활용
    0.50
     насы
    0.42
    展示
    0.42
    🖥
    0.42
     餐
    0.39
     XHTML
    0.39
    BLINK
    0.39
     Assets
    0.38
     Antibody
    0.38
     схе
    0.38
    POSITIVE LOGITS
     simbolo
    0.42
    0.41
    ktor
    0.41
    senha
    0.41
     cinco
    0.37
    footnotesize
    0.37
    hog
    0.37
     piedra
    0.37
    gerald
    0.37
    gradients
    0.36
    Act Density 0.038%

    No Known Activations