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

    Neuronpedia

    INDEX
    Explanations

    special formatted sections or elements in a document

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

    List formatting marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.66
     насељу
    -0.65
    Diweddarwch
    -0.65
    AnchorStyles
    -0.63
     дописавши
    -0.62
    хьтан
    -0.62
    genodigd
    -0.60
     Infórmanos
    -0.59
    Personensuche
    -0.59
    rungsseite
    -0.59
    POSITIVE LOGITS
     "
    0.42
    findpost
    0.38
    <strong>
    0.36
     question
    0.34
     (
    0.34
    SetPosition
    0.33
    da
    0.32
    !
    0.32
    alam
    0.32
     *
    0.32
    Act Density 0.016%

    No Known Activations