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

    Neuronpedia

    INDEX
    Explanations

    examples such as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ¹
    0.37
    avao
    0.36
    貥
    0.35
    able
    0.35
     ಈಗ
    0.34
    ır
    0.34
    的一部分
    0.34
     안정
    0.34
    angent
    0.33
     होकर
    0.33
    POSITIVE LOGITS
     semplice
    0.44
     fysis
    0.44
     frases
    0.43
     Diskussion
    0.43
     einfacher
    0.43
     petri
    0.43
     semplici
    0.42
     kombin
    0.42
    简单的
    0.41
     precios
    0.40
    Act Density 0.000%

    No Known Activations