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

    Neuronpedia

    INDEX
    Explanations

    mentions of science and scientific research

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

    science

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    --
    -0.44
     preferred
    -0.44
    ⤹
    -0.41
    ---
    -0.41
     comod
    -0.40
     mentioned
    -0.39
     Dwyer
    -0.38
     erwäh
    -0.38
     either
    -0.37
     minhas
    -0.37
    POSITIVE LOGITS
     science
    1.19
    science
    1.07
     ciencia
    0.88
     SCIENCE
    0.79
     scientific
    0.79
     sciences
    0.79
     scientists
    0.78
     scienza
    0.74
     biology
    0.74
    SCIENCE
    0.73
    Act Density 0.018%

    No Known Activations