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

    Neuronpedia

    INDEX
    Explanations

    pollution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ä
    -0.06
    -0.06
    ¤
    -0.06
    ْب
    -0.06
    τσι
    -0.06
     císa
    -0.06
    τσ
    -0.06
    timeout
    -0.06
    ugas
    -0.06
    άσ
    -0.06
    POSITIVE LOGITS
     Turning
    0.07
    DataSource
    0.07
    .link
    0.07
    -www
    0.06
     instincts
    0.06
     Feature
    0.06
     autonomy
    0.06
    *width
    0.06
    getData
    0.06
    ils
    0.06
    Act Density 0.020%

    No Known Activations