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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Now
    0.47
     Error
    0.44
     ;
    0.43
     $
    0.43
     \\
    0.43
     }
    0.42
     R
    0.42
     .
    0.42
    R
    0.42
     \
    0.41
    POSITIVE LOGITS
    шенные
    0.45
     defies
    0.45
     aspires
    0.44
     రూపాయ
    0.42
     sounded
    0.42
     likened
    0.41
     nineties
    0.41
    шенный
    0.41
     confuses
    0.41
     fifties
    0.40
    Act Density 0.014%

    No Known Activations