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

    Neuronpedia

    INDEX
    Explanations

    import statements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    import as user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     organizers
    -0.46
     disparate
    -0.44
    ựng
    -0.42
     grasp
    -0.42
     partenza
    -0.41
     Regel
    -0.41
     vigour
    -0.41
    endregion
    -0.41
     base
    -0.41
    toBeTruthy
    -0.41
    POSITIVE LOGITS
    GOTREF
    0.62
    ViewFeatures
    0.59
    adaptiveStyles
    0.58
     utafitiHapana
    0.57
    Personendaten
    0.56
    rungsseite
    0.54
    tagHelperRunner
    0.53
     ***!
    0.52
     Numerade
    0.52
     Roskov
    0.52
    Act Density 0.000%

    No Known Activations