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

    Neuronpedia

    INDEX
    Explanations

    specific numeric values and symbols related to measurements or statistics

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

    Numbers starting with "18"

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by punctuation or other numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Buona
    -0.51
     CONSE
    -0.48
    underwater
    -0.47
    Buddha
    -0.47
     समीक्षाएं
    -0.47
    Groetjes
    -0.46
    Royaume
    -0.46
    blusa
    -0.45
    check
    -0.45
    Underlying
    -0.45
    POSITIVE LOGITS
    mpe
    0.52
    SerializedName
    0.47
    beitet
    0.46
    0.45
     Julian
    0.44
    aarrggbb
    0.43
     Marsden
    0.43
    TINGS
    0.43
     Elizabethan
    0.42
    entieth
    0.42
    Act Density 0.569%

    No Known Activations