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

    Neuronpedia

    INDEX
    Explanations

    determiners and pronouns

    np_acts-logits-general · gemini-2.5-flash-lite

    detailed step-by-step instructions and comprehensive explanations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @chidakshravuru
    New Auto-Interp
    Negative Logits
     considerations
    0.49
     consideration
    0.47
    perhaps
    0.46
     whilst
    0.43
     rudimentary
    0.43
    based
    0.42
     pullback
    0.41
     scenario
    0.41
     socalled
    0.41
    initial
    0.41
    POSITIVE LOGITS
      
    1.04
     They
    1.03
     It
    1.01
     You
    1.01
     This
    0.97
     That
    0.97
     These
    0.91
     Of
    0.89
     Its
    0.89
     Their
    0.88
    Act Density 4.114%

    No Known Activations