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

    Neuronpedia

    INDEX
    Explanations

    STEM, STEAM disciplines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     problemat
    0.38
     ción
    0.36
    Question
    0.35
    ibranch
    0.35
     Bant
    0.34
    hann
    0.34
     observing
    0.34
    Dry
    0.33
    imodal
    0.33
     bimod
    0.33
    POSITIVE LOGITS
    <unused97>
    0.41
    science
    0.41
    STM
    0.39
     мол
    0.39
     मारे
    0.38
    zij
    0.38
    シナ
    0.38
     noire
    0.38
     przem
    0.38
    フト
    0.38
    Act Density 0.000%

    No Known Activations