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

    Neuronpedia

    INDEX
    Explanations

    code file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     embarked
    -0.07
    atus
    -0.07
     CES
    -0.07
     заказ
    -0.06
     нар
    -0.06
     slur
    -0.06
    rese
    -0.06
    black
    -0.06
    izont
    -0.06
    ATUS
    -0.06
    POSITIVE LOGITS
    .unlink
    0.07
    Pending
    0.07
    /static
    0.07
    ileged
    0.07
    =?,
    0.06
     Sesso
    0.06
    .tech
    0.06
    StateToProps
    0.06
    /gin
    0.06
    EditingStyle
    0.06
    Act Density 0.056%

    No Known Activations