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

    Neuronpedia

    INDEX
    Explanations

    passages discussing science and scientific concepts

    oai_token-act-pair · gemini-2.0-flash

    science-related topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scientific
    -2.11
     science
    -1.99
    scientific
    -1.94
    science
    -1.88
     Science
    -1.88
     scientists
    -1.88
    Scientific
    -1.86
     Scientific
    -1.84
    Science
    -1.84
     scientist
    -1.81
    POSITIVE LOGITS
    Datuak
    0.66
    enumii
    0.65
    onAttach
    0.56
     typelib
    0.54
    addCriterion
    0.53
    VIAF
    0.52
     Goats
    0.52
    oa̍t
    0.51
    kuuta
    0.49
     Lattice
    0.48
    Act Density 2.883%

    No Known Activations