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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lab
    -0.07
     xhttp
    -0.07
    _down
    -0.07
     kInstruction
    -0.07
    注
    -0.07
    鸤
    -0.07
     zach
    -0.07
    Explanation
    -0.07
    맑
    -0.06
     tys
    -0.06
    POSITIVE LOGITS
     drafting
    0.07
    oldt
    0.06
    """)↵
    0.06
    都没
    0.06
    "]=$
    0.06
    껭
    0.06
    ARI
    0.06
     Warrior
    0.06
     traveler
    0.06
     Harvey
    0.06
    Act Density 0.043%

    No Known Activations