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

    Neuronpedia

    INDEX
    Explanations

    Code/structured data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wand
    -0.07
     upd
    -0.07
    ə
    -0.07
     secre
    -0.06
    expiration
    -0.06
     Warp
    -0.06
     alignments
    -0.06
     padd
    -0.06
     membr
    -0.06
     declines
    -0.06
    POSITIVE LOGITS
    하게
    0.07
    quette
    0.07
    rouch
    0.07
    _dropdown
    0.07
    claimed
    0.06
    anked
    0.06
     Medicaid
    0.06
     replacements
    0.06
     dispozici
    0.06
    efined
    0.06
    Act Density 0.000%

    No Known Activations