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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ороз
    -0.06
    Directed
    -0.06
     elem
    -0.06
     ตร
    -0.06
    -forward
    -0.06
     square
    -0.06
    (second
    -0.06
    xdd
    -0.06
     descend
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    _accepted
    0.07
    .**************↵
    0.07
    accom
    0.07
    olist
    0.07
    ị
    0.07
    ΑΙ
    0.07
    tery
    0.07
    ernet
    0.06
     meticulously
    0.06
    ]!='
    0.06
    Act Density 0.006%

    No Known Activations