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

    Neuronpedia

    INDEX
    Explanations

    text from cursor to line end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    APPROVAL
    0.43
    ेट्टी
    0.41
     sorte
    0.41
    িন্দা
    0.40
     شناخت
    0.40
    gradation
    0.40
    REFER
    0.39
    nikom
    0.39
    epar
    0.38
     povos
    0.38
    POSITIVE LOGITS
     End
    0.45
     Mural
    0.43
     StyleSheet
    0.41
     Psalm
    0.40
     Revis
    0.39
     Brace
    0.39
     Editor
    0.38
    镜头
    0.38
     Mus
    0.38
     Vign
    0.38
    Act Density 0.001%

    No Known Activations