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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing knowledge or awareness

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

    knowing things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gynhyrchwyd
    -0.42
     Verso
    -0.40
    Hochspringen
    -0.40
    SharedCtor
    -0.40
     ligiloj
    -0.39
     voto
    -0.38
     Kunde
    -0.36
     overall
    -0.35
     pino
    -0.35
     matel
    -0.35
    POSITIVE LOGITS
    AndEndTag
    0.76
    HomeAsUpEnabled
    0.58
     sappiamo
    0.56
     conocemos
    0.52
     esquecer
    0.50
     verdadeira
    0.50
     sabem
    0.49
     bekannt
    0.49
     dimentic
    0.49
     spalle
    0.48
    Act Density 0.015%

    No Known Activations