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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Raphael
    -0.07
    .ResponseEntity
    -0.06
    Draft
    -0.06
    textBox
    -0.06
    .TextAlign
    -0.06
    тура
    -0.06
     �
    -0.06
     requ
    -0.06
    année
    -0.06
     Rene
    -0.06
    POSITIVE LOGITS
     by
    0.14
     By
    0.09
     BY
    0.09
    BY
    0.09
    -by
    0.07
    by
    0.07
    Sky
    0.07
     DR
    0.07
    By
    0.07
    /img
    0.07
    Act Density 0.091%

    No Known Activations