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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and operations

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

    mathematical definitions and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.89
    CloseOperation
    -0.59
    愷
    -0.54
    thâu
    -0.54
     autorytatywna
    -0.53
    IntoConstraints
    -0.52
     Normdatei
    -0.51
    ագրություններ
    -0.50
     AssemblyCulture
    -0.49
    الحياه
    -0.49
    POSITIVE LOGITS
     wound
    0.38
     fumée
    0.37
     Pistol
    0.36
     Got
    0.35
     Ditto
    0.35
    Lieu
    0.34
    刀
    0.34
    Fug
    0.34
    Got
    0.34
     Simply
    0.34
    Act Density 0.003%

    No Known Activations