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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Def
    -0.07
     progressBar
    -0.07
     bridges
    -0.06
    }↵↵↵↵↵
    -0.06
    :x
    -0.06
    특별시
    -0.06
     Essence
    -0.06
     situated
    -0.06
     idx
    -0.06
     Newton
    -0.06
    POSITIVE LOGITS
     ged
    0.07
     설정
    0.06
     sau
    0.06
    (part
    0.06
     đức
    0.06
     Bản
    0.06
    IFICATIONS
    0.06
    OnChange
    0.06
    ใต
    0.06
     �
    0.06
    Act Density 0.117%

    No Known Activations