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

    Neuronpedia

    INDEX
    Explanations

    various symbols and characters commonly used in formatting or referencing items, particularly in lists or data presentations

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

    citations and footnotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.61
    findpost
    -0.57
    enumii
    -0.54
    ]")]
    -0.51
    enumi
    -0.49
    Distribuzione
    -0.49
     onBind
    -0.48
     ſind
    -0.48
     بيها
    -0.48
    ſcher
    -0.48
    POSITIVE LOGITS
     Италијани
    0.68
    preuves
    0.36
     Prime
    0.35
    *,
    0.34
    zeichnungen
    0.34
     perna
    0.33
    ?,?,
    0.33
    intervento
    0.33
    ByExample
    0.33
    elemField
    0.32
    Act Density 0.147%

    No Known Activations