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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ーロ
    -0.07
    cleanup
    -0.07
    elease
    -0.06
     annunci
    -0.06
    claration
    -0.06
    ections
    -0.06
    occup
    -0.06
     enam
    -0.06
    ора
    -0.06
    leftright
    -0.06
    POSITIVE LOGITS
    uppy
    0.07
     ss
    0.06
    _typ
    0.06
     Lafayette
    0.06
    subpackage
    0.06
     tslint
    0.06
    =v
    0.06
    $arr
    0.06
    zs
    0.06
    _chance
    0.06
    Act Density 0.003%

    No Known Activations