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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interpreted
    -0.07
    ují
    -0.07
     reforms
    -0.06
    inement
    -0.06
     compromise
    -0.06
    White
    -0.06
    Smith
    -0.06
    ازم
    -0.06
     medidas
    -0.06
     hairstyles
    -0.06
    POSITIVE LOGITS
     लगत
    0.07
     chlap
    0.07
    .mix
    0.07
    .KeyCode
    0.06
    (exc
    0.06
    ्ध
    0.06
    การจ
    0.06
    -parent
    0.06
     đăng
    0.06
     ngược
    0.06
    Act Density 0.066%

    No Known Activations