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

    Neuronpedia

    INDEX
    Explanations

    terms related to heterogeneity

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

    heter followed by scientific suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fü
    -0.45
     noDo
    -0.45
    UrlResolution
    -0.42
     bookId
    -0.41
     pila
    -0.41
     palme
    -0.41
     Palme
    -0.40
    Autoritní
    -0.39
    printList
    -0.39
     برانيه
    -0.39
    POSITIVE LOGITS
     heter
    2.36
     Heter
    2.20
    heter
    2.06
    Heter
    2.05
     Hetero
    1.75
    Hetero
    1.60
     heterogeneous
    1.56
     hetero
    1.53
     heterogeneity
    1.45
     heterosexual
    1.16
    Act Density 0.008%

    No Known Activations