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

    Neuronpedia

    INDEX
    Explanations

    expressions of wanting or wishing to know something

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

    expressing past intentions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    estacks
    -0.55
    mbggenerated
    -0.50
    Tikang
    -0.49
     legyen
    -0.46
     inmiddels
    -0.45
    TemporalType
    -0.45
     strijd
    -0.45
    arraycopy
    -0.44
    aarrggbb
    -0.44
     énergétique
    -0.43
    POSITIVE LOGITS
     originally
    0.49
     thought
    0.49
     Originally
    0.48
    Originally
    0.47
     intended
    0.47
     Was
    0.46
     tadi
    0.45
    Was
    0.45
     recently
    0.44
     thoughts
    0.44
    Act Density 0.038%

    No Known Activations