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

    Neuronpedia

    INDEX
    Explanations

    drives, data, number, set, rule, address, hand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urs
    1.10
     ▸
    0.97
    𝙤
    0.91
    olen
    0.89
     ➤
    0.89
     RNAs
    0.81
    ✶
    0.80
    ♧
    0.80
    یش
    0.79
    ia
    0.79
    POSITIVE LOGITS
    тся
    0.92
    LER
    0.92
     proliferate
    0.92
     Valores
    0.87
    IDADE
    0.84
     flurry
    0.83
    唔
    0.81
     deceive
    0.80
     चीज़
    0.78
    ÇÃO
    0.78
    Act Density 0.057%

    No Known Activations