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

    Neuronpedia

    INDEX
    Explanations

    technical language, rules, and specific concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Расійскай
    0.52
    国
    0.47
     እስከ
    0.45
    തു
    0.44
     конкурен
    0.44
     Міні
    0.43
    רו
    0.42
    국
    0.42
    0.42
    чну
    0.42
    POSITIVE LOGITS
     modulus
    0.45
     endpoints
    0.45
    CallSettings
    0.44
     cube
    0.43
     morphism
    0.43
     ego
    0.42
     iodide
    0.41
     skl
    0.41
     algebraic
    0.41
     ethers
    0.40
    Act Density 0.000%

    No Known Activations