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

    Neuronpedia

    INDEX
    Explanations

    structured build

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sun
    0.52
    larını
    0.49
    விய
    0.47
     Bereich
    0.47
     Agencia
    0.46
     divina
    0.46
     Detalles
    0.46
     Shreve
    0.45
     Gründung
    0.45
     Figuren
    0.45
    POSITIVE LOGITS
    addTo
    0.45
    AES
    0.44
     সত্ত্বেও
    0.42
     affrontare
    0.41
     ಸಾಧ್ಯ
    0.40
     potentially
    0.39
     incubating
    0.38
    uff
    0.38
     αί
    0.38
    ୍କ
    0.38
    Act Density 0.005%

    No Known Activations