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

    Neuronpedia

    INDEX
    Explanations

    characters related to specific entities or names in a legal or formal context

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

    words like Jackson and Castlman

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     препратки
    -0.85
     يتيمه
    -0.84
     glyphicon
    -0.77
    AddHtmlAttribute
    -0.75
    __(/*!
    -0.74
    ロウィン
    -0.74
    ſicht
    -0.73
    <unused79>
    -0.71
    <unused42>
    -0.71
    [@BOS@]
    -0.71
    POSITIVE LOGITS
     fapt
    0.38
    bn
    0.35
    Sc
    0.35
    t
    0.34
     Glaubens
    0.33
    WH
    0.32
    R
    0.32
     Italij
    0.31
    J
    0.31
    ingga
    0.31
    Act Density 0.156%

    No Known Activations