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

    Neuronpedia

    INDEX
    Explanations

    a specific period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erevan
    0.42
    andaag
    0.41
    warranty
    0.40
     കണ്ട
    0.40
     visto
    0.40
     zawsze
    0.39
    gegevens
    0.39
     maharaja
    0.39
    aliana
    0.39
    ファミリー
    0.38
    POSITIVE LOGITS
     Ent
    0.45
    </code>
    0.43
     ent
    0.40
     damping
    0.40
    }`,
    0.39
    Ent
    0.39
     Board
    0.37
     qui
    0.36
     cet
    0.36
     способ
    0.36
    Act Density 0.000%

    No Known Activations