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

    Neuronpedia

    INDEX
    Explanations

    academic publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jaune
    -0.06
     duplicates
    -0.06
     örgüt
    -0.06
     uncomp
    -0.06
     dur
    -0.06
    (descriptor
    -0.06
    気持ち
    -0.06
    是在
    -0.06
    Overview
    -0.05
    ildo
    -0.05
    POSITIVE LOGITS
    _classification
    0.07
    .KEY
    0.07
    _cleanup
    0.06
     바랍니다
    0.06
    PTION
    0.06
     disciple
    0.06
    ModelIndex
    0.06
    _WM
    0.06
    -de
    0.06
     आवश
    0.06
    Act Density 0.005%

    No Known Activations