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

    Neuronpedia

    INDEX
    Explanations

    pivotal moments or key points in discussions

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

    conjunctions and common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.65
     Италијани
    -0.65
    OGND
    -0.64
    PreInfinity
    -0.62
    хьтан
    -0.61
    :✨
    -0.61
    kháu
    -0.59
    JAKARTA
    -0.57
    ChildScrollView
    -0.56
    ➟
    -0.56
    POSITIVE LOGITS
     dAtA
    0.36
     Bidang
    0.33
    untung
    0.32
    AccessorTable
    0.29
     And
    0.28
     Garantía
    0.27
    os
    0.27
    ...
    0.27
    ion
    0.27
     ...
    0.26
    Act Density 0.164%

    No Known Activations