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

    Neuronpedia

    INDEX
    Explanations

    scanf input formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     domanda
    0.44
    問
    0.43
    ถาม
    0.43
    вы
    0.41
    exported
    0.40
    问
    0.40
    UIAlert
    0.39
    抜け
    0.39
    asked
    0.38
     huk
    0.38
    POSITIVE LOGITS
     scanning
    0.59
     scanners
    0.56
     scan
    0.54
     scans
    0.54
     Scanning
    0.53
    scanning
    0.53
    扫描
    0.50
    Scanning
    0.50
     Scan
    0.48
     स्कैन
    0.46
    Act Density 0.003%

    No Known Activations