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

    Neuronpedia

    INDEX
    Explanations

    specific formatting characters and structures commonly used in documents

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

    section markers and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.45
     arşivlendi
    -0.44
    PointerException
    -0.43
     ModelExpression
    -0.43
    RefNanny
    -0.42
    kuuta
    -0.40
     thereon
    -0.40
    userdetails
    -0.40
    VersionUID
    -0.40
    ContentLoaded
    -0.39
    POSITIVE LOGITS
     autorytatywna
    0.65
    Autoritní
    0.49
     gynhyrchwyd
    0.48
     leſs
    0.47
     Infórmanos
    0.46
    +#+
    0.46
     Methuen
    0.42
    cyl
    0.42
     CanadaChoose
    0.41
     lizenzfreies
    0.41
    Act Density 0.458%

    No Known Activations