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

    Neuronpedia

    INDEX
    Explanations

    Non-English languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    三级
    -0.07
     FormGroup
    -0.06
     Nice
    -0.06
     fruitful
    -0.06
     ben
    -0.06
    inci
    -0.06
     수상
    -0.06
     crc
    -0.06
    ρό
    -0.06
     infantry
    -0.06
    POSITIVE LOGITS
    ulsion
    0.07
    development
    0.06
    capture
    0.06
     ži
    0.06
    rocessing
    0.06
     \/
    0.06
    onation
    0.06
     unbelie
    0.06
     administer
    0.06
    -create
    0.06
    Act Density 0.064%

    No Known Activations