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

    Neuronpedia

    INDEX
    Explanations

    terms related to data privacy and security in various contexts

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

    "initial" or "early"

    np_acts-logits-general · gemini-2.0-flash

    initial and early stages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    JspWriter
    -0.65
     snippetHide
    -0.61
    脚注の使い方
    -0.56
    ThemeOverlay
    -0.47
     незавершена
    -0.46
     فريبيس
    -0.45
    ValueStyle
    -0.44
    vrigt
    -0.44
     autorytatywna
    -0.44
    complexContent
    -0.43
    POSITIVE LOGITS
     initial
    2.96
     initially
    2.74
    initial
    2.54
    Initial
    2.47
     first
    2.44
     Initial
    2.40
     Initially
    2.32
     iniziale
    2.31
     inicial
    2.26
    Initially
    2.23
    Act Density 1.105%

    No Known Activations