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

    Neuronpedia

    INDEX
    Explanations

    key terms related to quality and effectiveness in various contexts

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

    makes [adjective]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.60
    autaire
    -0.49
     Hadrian
    -0.49
    ContextCompat
    -0.48
    FilterChain
    -0.48
     FUT
    -0.47
     pylint
    -0.47
    ScopeManager
    -0.46
    emale
    -0.46
     Fut
    -0.46
    POSITIVE LOGITS
     obdob
    0.42
     veľa
    0.37
    Naissance
    0.36
     beeld
    0.36
     afstand
    0.36
    istoitu
    0.35
     órg
    0.35
     fluxo
    0.34
     objav
    0.34
    gól
    0.34
    Act Density 0.124%

    No Known Activations