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

    Neuronpedia

    INDEX
    Explanations

    mathematical variables and operations within expressions

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

    Mathematical or symbolic expressions

    np_acts-logits-general · gemini-2.0-flash

    prime numbers and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    richTextPanel
    -0.42
    \{\\
    -0.42
     techniczne
    -0.40
     fotográfica
    -0.40
     Độ
    -0.40
    Linki
    -0.38
     Comprometido
    -0.37
    Przypisy
    -0.37
    ďaka
    -0.36
     prosím
    -0.36
    POSITIVE LOGITS
    GTCX
    0.71
     propOrder
    0.54
     Joc
    0.50
     TAI
    0.47
     disarm
    0.46
     Throwable
    0.45
     Taktlose
    0.45
     ſhall
    0.43
     shame
    0.43
    fieras
    0.43
    Act Density 2.037%

    No Known Activations