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

    Neuronpedia

    INDEX
    Explanations

    references to clarification, notes, and technical details

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

    Introductory interjections before a statement

    np_acts-logits-general · gemini-2.0-flash

    side notes, clarifications, and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.62
    SafeMath
    -0.56
    蚪
    -0.55
     händer
    -0.54
    principalColumn
    -0.52
     læng
    -0.52
     miniaturka
    -0.52
     asesinado
    -0.52
    ientras
    -0.51
     Reſ
    -0.51
    POSITIVE LOGITS
    :
    0.52
    一下
    0.39
    0.39
     <<<<<<<<<<<<<<
    0.37
     speaking
    0.36
    httphttps
    0.36
     Seit
    0.35
     sappi
    0.35
    AppMethodBeat
    0.35
    :
    0.34
    Act Density 0.339%

    No Known Activations