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

    Neuronpedia

    INDEX
    Explanations

    When

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FileUtils
    -0.07
     Vari
    -0.06
    znik
    -0.06
    wives
    -0.06
     Hoàng
    -0.06
     cung
    -0.06
    važ
    -0.06
     Weg
    -0.06
    findAll
    -0.06
    وقع
    -0.06
    POSITIVE LOGITS
     blindness
    0.07
    asjon
    0.06
     portion
    0.06
    .No
    0.06
    Requirements
    0.06
    终
    0.06
    Net
    0.06
    ered
    0.06
     overhead
    0.06
    --------------------
    0.06
    Act Density 0.177%

    No Known Activations