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

    Neuronpedia

    INDEX
    Explanations

    Institutes and associations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     clumps
    0.51
     flakes
    0.49
     anger
    0.49
     pixie
    0.49
     biasa
    0.48
     posse
    0.46
     hangout
    0.46
     superposition
    0.46
     slang
    0.46
     sbagli
    0.46
    POSITIVE LOGITS
     Sciences
    0.60
     Research
    0.53
     Fisheries
    0.51
     एवं
    0.49
     Education
    0.48
     &
    0.47
     Affairs
    0.47
     Science
    0.46
    cience
    0.45
     \&
    0.45
    Act Density 0.148%

    No Known Activations