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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -month
    -0.07
    roducing
    -0.07
    -core
    -0.07
     persistent
    -0.07
    958
    -0.07
    Nama
    -0.06
    енсив
    -0.06
    046
    -0.06
    idas
    -0.06
    idy
    -0.06
    POSITIVE LOGITS
     إليه
    0.08
     Disabilities
    0.07
    levelname
    0.07
    )){↵↵
    0.07
    주는
    0.07
    :B
    0.07
     travel
    0.06
     templateUrl
    0.06
    '),('
    0.06
    )[-
    0.06
    Act Density 0.055%

    No Known Activations