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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    poons
    -0.07
     writ
    -0.07
     retailers
    -0.07
     accomp
    -0.06
    やって
    -0.06
    orld
    -0.06
     relev
    -0.06
     лі
    -0.06
     reputation
    -0.06
     Week
    -0.06
    POSITIVE LOGITS
    (pm
    0.06
     adb
    0.06
    sch
    0.06
     м
    0.06
    ньо
    0.06
    Growing
    0.06
    ."↵↵↵↵
    0.06
     stared
    0.06
     ));↵
    0.06
    ##↵
    0.06
    Act Density 0.000%

    No Known Activations