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

    Neuronpedia

    INDEX
    Explanations

    Colon and quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     开
    -0.07
    Fc
    -0.06
     Socorro
    -0.06
     się
    -0.06
    ////////////////////////////////////////////////////////////////////
    -0.06
    査
    -0.06
     iP
    -0.06
    ﾑ
    -0.06
     lle
    -0.06
     ds
    -0.06
    POSITIVE LOGITS
    kim
    0.07
    sis
    0.07
     vergi
    0.06
    .empty
    0.06
     الوز
    0.06
    وذ
    0.06
     Angeles
    0.06
    .SOCK
    0.06
    .confirm
    0.06
    compressed
    0.06
    Act Density 0.276%

    No Known Activations