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
     powdered
    -0.07
    ículo
    -0.06
    keit
    -0.06
     automobile
    -0.06
    तम
    -0.06
    初始化
    -0.06
    ybrid
    -0.06
     Chain
    -0.06
    based
    -0.06
     strike
    -0.06
    POSITIVE LOGITS
    [length
    0.07
     пят
    0.06
    (matches
    0.06
     grac
    0.06
     datings
    0.06
     以
    0.06
     wg
    0.06
     UIAlertAction
    0.06
    .getLength
    0.06
    цией
    0.06
    Act Density 0.011%

    No Known Activations