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

    Neuronpedia

    INDEX
    Explanations

    normalization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    纤
    -0.26
    caled
    -0.25
    habi
    -0.25
    辦çIJĨ
    -0.24
    rail
    -0.24
    Æ°á»Ŀ
    -0.24
    æĶ¯çº¿
    -0.24
    êµ°
    -0.24
    .sprite
    -0.23
    ModelIndex
    -0.23
    POSITIVE LOGITS
    ars
    0.26
    $$$
    0.25
     Ko
    0.25
    èĢĮåĩº
    0.24
     Ment
    0.24
    .Surface
    0.23
     scooter
    0.23
    æIJģ
    0.23
     wen
    0.23
     pep
    0.23
    Act Density 0.005%

    No Known Activations