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

    Neuronpedia

    INDEX
    Explanations

    personal experiences and reflections about parenting and related products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    before end of turn

    np_acts-logits-general · gemini-2.0-flash

    interested in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.83
    WithIOException
    -0.75
     Wikimedijinoj
    -0.74
     مرئيه
    -0.67
    tanleria
    -0.66
    IndentedString
    -0.66
    хьтан
    -0.65
     Roskov
    -0.65
     ligiloj
    -0.65
     <<<<<<<<<<<<<<
    -0.65
    POSITIVE LOGITS
     Matt
    0.34
     عص
    0.33
     hope
    0.33
     g
    0.33
     THEORY
    0.33
    ↵
    0.32
     sa
    0.32
     Bau
    0.32
     I
    0.31
    Matt
    0.31
    Act Density 0.197%

    No Known Activations