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

    Neuronpedia

    INDEX
    Explanations

    phrases related to research studies and evaluation of outcomes

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

    Beginning of research goals

    np_acts-logits-general · gemini-2.0-flash

    study aims and objectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.70
    SequentialGroup
    -0.66
     estekak
    -0.60
    hoeddwyd
    -0.57
     dAtA
    -0.57
     >=",
    -0.56
     BrowserModule
    -0.56
     AssemblyCulture
    -0.55
    脚注の使い方
    -0.54
    digans
    -0.52
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.36
     purpose
    0.34
     present
    0.33
     primarily
    0.32
     provide
    0.32
     show
    0.32
     aims
    0.32
     purposes
    0.32
     mainly
    0.32
     chiefly
    0.30
    Act Density 0.367%

    No Known Activations