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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    데이트
    -0.08
    quee
    -0.06
     lou
    -0.06
    об
    -0.06
     Mack
    -0.06
    -pro
    -0.06
    808
    -0.06
     هایی
    -0.06
     более
    -0.06
     Tobias
    -0.06
    POSITIVE LOGITS
    ;
    0.09
    гляд
    0.07
     examine
    0.07
    Existing
    0.07
     at
    0.07
    *);↵↵
    0.07
     Viewing
    0.07
     Using
    0.07
     examining
    0.07
    Att
    0.06
    Act Density 0.013%

    No Known Activations