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

    Neuronpedia

    INDEX
    Explanations

    br

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⌣
    -0.07
    ﾟ
    -0.07
    uable
    -0.07
     cruel
    -0.06
    周围
    -0.06
     hides
    -0.06
    (Icons
    -0.06
    ὶ
    -0.06
     anatom
    -0.06
    笑容
    -0.06
    POSITIVE LOGITS
     lecken
    0.08
    这两
    0.07
    🤖
    0.07
    ][-
    0.07
    骒
    0.07
    金
    0.07
     transmitter
    0.07
    쎌
    0.06
    =h
    0.06
    整个人
    0.06
    Act Density 0.014%

    No Known Activations