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

    Neuronpedia

    INDEX
    Explanations

    themes related to abstract concepts and their real-world applications

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

    theory and practice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    appé
    -0.38
    setProgress
    -0.33
     retr
    -0.32
     biling
    -0.30
    intios
    -0.30
    重点
    -0.30
     tartalomajánló
    -0.30
    횟
    -0.30
    esac
    -0.30
    hető
    -0.29
    POSITIVE LOGITS
     theoretical
    2.00
    theoretical
    1.86
     theory
    1.72
     theore
    1.67
    theory
    1.66
     Theoretical
    1.65
    Theoretical
    1.61
    理论
    1.56
     teórico
    1.52
     teoría
    1.51
    Act Density 0.109%

    No Known Activations