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

    Neuronpedia

    INDEX
    Explanations

    version

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Democr
    -0.07
     води
    -0.06
     шляхом
    -0.06
    foot
    -0.06
    unuz
    -0.06
     Ivan
    -0.06
    غيرة
    -0.06
    徒
    -0.06
     모든
    -0.06
     mushrooms
    -0.06
    POSITIVE LOGITS
    _SUCCESS
    0.07
     autobiography
    0.06
    PLEMENT
    0.06
    rists
    0.06
    arnation
    0.06
    _l
    0.06
    \Framework
    0.06
    чивается
    0.06
     endDate
    0.06
    彻
    0.06
    Act Density 0.001%

    No Known Activations