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

    Neuronpedia

    INDEX
    Explanations

    thickness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Commit
    -0.07
     exhilar
    -0.06
     raising
    -0.06
    Mot
    -0.06
    quin
    -0.06
     astore
    -0.06
    _gem
    -0.06
    IDI
    -0.06
    ают
    -0.06
    pane
    -0.06
    POSITIVE LOGITS
     thickness
    0.17
     Thickness
    0.15
    Thickness
    0.14
    _thickness
    0.10
    thickness
    0.10
    ickness
    0.10
    압
    0.07
     worrying
    0.07
     мм
    0.07
     тол
    0.06
    Act Density 0.003%

    No Known Activations