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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    bearer
    -0.07
    entů
    -0.07
    \Repository
    -0.06
    165
    -0.06
     громадян
    -0.06
     Cowboy
    -0.06
    onden
    -0.06
    complete
    -0.06
    ī
    -0.06
    POSITIVE LOGITS
     electrode
    0.07
     OUTER
    0.06
     finale
    0.06
     cosmetic
    0.06
    EDGE
    0.06
    ABLE
    0.06
     helium
    0.06
    _articles
    0.06
    _UL
    0.06
     wastewater
    0.06
    Act Density 0.022%

    No Known Activations