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

    Neuronpedia

    INDEX
    Explanations

    rather than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     동일
    0.36
     identical
    0.35
     абсолютно
    0.34
    ？
    0.34
    identical
    0.34
     Acacia
    0.34
    やつ
    0.34
     Socket
    0.33
    的不同
    0.33
    <0x99>
    0.33
    POSITIVE LOGITS
     rather
    1.45
     instead
    1.28
     plutôt
    1.23
    而不是
    1.21
    rather
    1.20
    Rather
    1.19
     вместо
    1.17
     piuttosto
    1.17
    而非
    1.12
     Rather
    1.10
    Act Density 0.238%

    No Known Activations