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

    Neuronpedia

    INDEX
    Explanations

    complex relationships within data and references to constraints or conditions

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

    preceding tokens like "with" or abbreviations

    np_acts-logits-general · gemini-2.0-flash

    geometric terms and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    τία
    -0.70
    ωση
    -0.66
    θεση
    -0.53
    λία
    -0.52
     particuliers
    -0.51
     Tuttle
    -0.50
    τηση
    -0.50
     supérieurs
    -0.50
     obstante
    -0.50
     SwitchCompat
    -0.49
    POSITIVE LOGITS
    DockStyle
    0.65
    acji
    0.61
     Normdatei
    0.61
    AndEndTag
    0.61
     OFDb
    0.59
    сылкі
    0.59
    unii
    0.59
     <=",
    0.56
    Спасылкі
    0.54
    ifornie
    0.54
    Act Density 0.042%

    No Known Activations