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

    Neuronpedia

    INDEX
    Explanations

    Bod

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unf
    -0.07
     rat
    -0.07
    ELSE
    -0.06
    nict
    -0.06
     polym
    -0.06
     inequality
    -0.06
     PROFITS
    -0.06
    +r
    -0.06
    Invariant
    -0.06
     UF
    -0.06
    POSITIVE LOGITS
    od
    0.12
    OD
    0.10
     Lod
    0.09
     broth
    0.08
     Kod
    0.07
     Hod
    0.07
    št
    0.07
     Sed
    0.07
    _OD
    0.07
     vod
    0.07
    Act Density 0.031%

    No Known Activations