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

    Neuronpedia

    INDEX
    Explanations

    societal issues, relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     غربی
    -0.08
    ा�
    -0.07
    CLK
    -0.07
    RGBA
    -0.07
    rito
    -0.07
    incerely
    -0.07
    yang
    -0.07
    æk
    -0.07
     Zoe
    -0.07
    _helpers
    -0.06
    POSITIVE LOGITS
     Resorts
    0.06
     induced
    0.06
     politique
    0.06
    rights
    0.06
     busted
    0.06
    \param
    0.06
     bookmark
    0.06
    (script
    0.06
     maximal
    0.06
     debt
    0.06
    Act Density 0.019%

    No Known Activations