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

    Neuronpedia

    INDEX
    Explanations

    parentheses and colons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (or
    -0.07
     wParam
    -0.07
     ho
    -0.07
    گرد
    -0.07
     ******************************************************************************/↵↵
    -0.07
     lưới
    -0.07
    togroup
    -0.06
     wider
    -0.06
     wonderfully
    -0.06
    "`↵
    -0.06
    POSITIVE LOGITS
     decl
    0.07
     Loaded
    0.07
    邪
    0.07
     Branch
    0.06
     etki
    0.06
     ソ
    0.06
    Service
    0.06
    GE
    0.06
     invoke
    0.06
    Anti
    0.06
    Act Density 0.017%

    No Known Activations