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

    Neuronpedia

    INDEX
    Explanations

    students who, address the, cities, creativity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Prz
    0.54
    posizione
    0.53
    ቖ
    0.50
     ორგანო
    0.50
    łon
    0.49
    Dónde
    0.48
    ACIÓN
    0.46
    Resultado
    0.46
    Contacto
    0.46
     സ്ഥല
    0.45
    POSITIVE LOGITS
    i
    0.52
    '
    0.47
    sp
    0.45
    s
    0.45
    si
    0.44
    oe
    0.43
    intermediate
    0.42
    j
    0.41
    sh
    0.40
    oran
    0.40
    Act Density 0.013%

    No Known Activations