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

    Neuronpedia

    INDEX
    Explanations

    format output strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UTF
    -0.11
     Muk
    -0.10
     UTF
    -0.10
     pam
    -0.09
    ehler
    -0.09
     Dag
    -0.09
     Typ
    -0.09
    isper
    -0.09
    .toByteArray
    -0.09
     Pros
    -0.09
    POSITIVE LOGITS
     output
    0.17
    è¾ĵåĩº
    0.16
     Output
    0.15
     format
    0.15
     outputs
    0.15
    .Format
    0.15
    format
    0.14
    output
    0.14
    .format
    0.14
    Output
    0.13
    Act Density 0.066%

    No Known Activations