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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Perspective
    -0.08
    $l
    -0.07
     violated
    -0.06
     violates
    -0.06
    الك
    -0.06
    tember
    -0.06
     backing
    -0.06
     differently
    -0.06
     destek
    -0.06
    .Man
    -0.06
    POSITIVE LOGITS
    IOD
    0.07
     Yun
    0.06
    737
    0.06
    xD
    0.06
    uchos
    0.06
     resil
    0.06
     vysok
    0.06
    رى
    0.06
    ुट
    0.06
    +
    0.06
    Act Density 0.190%

    No Known Activations