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

    Neuronpedia

    INDEX
    Explanations

    sheer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -With
    -0.08
    깸
    -0.07
    tout
    -0.07
    🏺
    -0.07
    ﱡ
    -0.07
    classList
    -0.07
    🐋
    -0.07
     adjustments
    -0.07
    ⛲
    -0.07
     {};↵↵
    -0.07
    POSITIVE LOGITS
    (dec
    0.07
     eag
    0.07
    vertising
    0.07
     presses
    0.07
     '&#
    0.07
    eeper
    0.07
    дел
    0.07
    空军
    0.07
    -medium
    0.07
     believed
    0.07
    Act Density 0.007%

    No Known Activations