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

    Neuronpedia

    INDEX
    Explanations

    automating tasks and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.75
    ot
    0.55
     in
    0.54
    も
    0.54
    ও
    0.52
     в
    0.47
    ۳
    0.46
    <0xD5>
    0.46
    \
    0.45
    
    0.44
    POSITIVE LOGITS
     automaticamente
    0.54
     automatically
    0.52
     automático
    0.52
    自動
    0.50
     automáticamente
    0.49
     automaty
    0.49
     automatique
    0.48
    w
    0.48
     for
    0.48
     自動
    0.47
    Act Density 0.022%

    No Known Activations