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

    Neuronpedia

    INDEX
    Explanations

    speculative statements and hypotheses

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

    guess, speculate, hypothesize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    habitude
    -0.42
    MessageTagHelper
    -0.42
     Früchte
    -0.42
     fotográfica
    -0.42
     fotográfico
    -0.41
    WidgetItem
    -0.41
     senhora
    -0.40
     hidráulica
    -0.40
    olahan
    -0.39
     autoridade
    -0.38
    POSITIVE LOGITS
    GEBURTSDATUM
    0.91
     conject
    0.64
     guessing
    0.57
     guesses
    0.57
     guessed
    0.57
     speculation
    0.56
     conjecture
    0.56
     suspect
    0.56
    StructEnd
    0.56
     guess
    0.55
    Act Density 0.329%

    No Known Activations