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

    Neuronpedia

    INDEX
    Explanations

    fixed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    scape
    -0.07
     embr
    -0.07
     ecs
    -0.07
    Sz
    -0.07
     스트
    -0.07
     спеці
    -0.07
    .depart
    -0.07
    継
    -0.07
     cous
    -0.07
    Blue
    -0.06
    POSITIVE LOGITS
     �
    0.07
    ."]↵
    0.07
    移到
    0.07
     }}↵
    0.06
    월
    0.06
    ;}↵
    0.06
    .)↵
    0.06
    %.↵
    0.06
    .Vector
    0.06
    !)↵↵
    0.06
    Act Density 0.013%

    No Known Activations