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

    Neuronpedia

    INDEX
    Explanations

    electricity elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Manus
    -0.07
     aussi
    -0.06
     Erect
    -0.06
     WK
    -0.06
     Boxing
    -0.06
    itting
    -0.06
    復
    -0.06
    dense
    -0.06
    直接
    -0.06
    -first
    -0.06
    POSITIVE LOGITS
    >G
    0.07
     setState
    0.06
     wx
    0.06
     �
    0.06
     Producer
    0.06
     mains
    0.06
     cornerstone
    0.06
     Interviews
    0.06
    /st
    0.06
    країн
    0.06
    Act Density 0.056%

    No Known Activations