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

    Neuronpedia

    INDEX
    Explanations

    key components and terminology related to scientific research and methodology

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

    Text snippets preceding section headers

    np_acts-logits-general · gemini-2.0-flash

    technical terms and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     also
    -0.38
    ↵↵
    -0.38
     it
    -0.37
     оно
    -0.35
     eh
    -0.34
     Mul
    -0.34
     Meksiku
    -0.33
     Ap
    -0.33
     plus
    -0.33
     Hamm
    -0.32
    POSITIVE LOGITS
    WriteTagHelper
    0.69
     cherchés
    0.68
    ंदीखरीदारी
    0.67
    KURZBESCHREIBUNG
    0.67
    原始内容存档于
    0.66
    ftagPool
    0.64
    DeleteBehavior
    0.63
    новништво
    0.62
    +#+
    0.61
    EndInit
    0.60
    Act Density 0.327%

    No Known Activations