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

    Neuronpedia

    INDEX
    Explanations

    guidelines and warnings related to safety and legality in various contexts

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

    legal documentation and ethics statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    prefixer
    -0.38
    Gambas
    -0.34
     désolés
    -0.33
     Combien
    -0.32
     Erkennt
    -0.31
     partly
    -0.31
    ArrowToggle
    -0.31
     somewhat
    -0.30
    🗳
    -0.30
    sstelle
    -0.29
    POSITIVE LOGITS
    ftagPool
    0.68
     NSCoder
    0.65
    IUrlHelper
    0.58
     betweenstory
    0.58
    enumi
    0.57
    fromnode
    0.51
    GEBURTSDATUM
    0.50
     desmotivaciones
    0.49
     ſta
    0.49
     ainfi
    0.47
    Act Density 0.051%

    No Known Activations