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

    Neuronpedia

    INDEX
    Explanations

    omitted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RDD
    -0.06
     Fall
    -0.06
    Раз
    -0.06
    rror
    -0.06
     FIXME
    -0.06
     กร
    -0.06
     kısa
    -0.06
     accuse
    -0.06
     Раз
    -0.06
    ISOString
    -0.06
    POSITIVE LOGITS
    ivo
    0.07
     меня
    0.07
     adopted
    0.07
     Sample
    0.07
     questionnaire
    0.07
     exemption
    0.07
     knitting
    0.07
    asm
    0.07
    threads
    0.07
    .at
    0.07
    Act Density 0.002%

    No Known Activations