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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to law and order, along with suboptimal situations.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AutoScale
    -0.54
     فريبيس
    -0.52
     bezeichneter
    -0.52
    Nathaniel
    -0.51
    際
    -0.51
    nair
    -0.50
    unzione
    -0.49
     latine
    -0.49
    ViewFeatures
    -0.49
     année
    -0.49
    POSITIVE LOGITS
     FetchType
    0.61
    UnsafeEnabled
    0.52
    rition
    0.50
    Geplaatst
    0.49
    otheby
    0.48
    ContextHolder
    0.48
     estimés
    0.47
    הערות
    0.47
    tinyos
    0.46
    PreferredItem
    0.44
    Act Density 0.926%

    No Known Activations