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

    Neuronpedia

    INDEX
    Explanations

    physics and chemistry questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Finder
    0.34
     Sonic
    0.32
     Algorithm
    0.32
     Creative
    0.31
     Casino
    0.31
     ebben
    0.31
     Rady
    0.31
     Managed
    0.30
    ?}",
    0.30
     Creator
    0.30
    POSITIVE LOGITS
     principles
    0.59
    principles
    0.56
    적
    0.53
     princípios
    0.52
     concepts
    0.51
     principes
    0.51
     fundamentals
    0.50
     principios
    0.50
    പരമായ
    0.49
     jargon
    0.49
    Act Density 0.061%

    No Known Activations