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

    Neuronpedia

    INDEX
    Explanations

    various types of snacks and their components

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

    snack diversity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cust
    -0.29
     Rohan
    -0.28
     matching
    -0.25
    Bilan
    -0.25
     veterinario
    -0.25
     compéti
    -0.25
     managers
    -0.24
    tehen
    -0.24
     estancia
    -0.24
     custos
    -0.24
    POSITIVE LOGITS
     AssemblyCompany
    0.82
    Искәрмәләр
    0.77
     surla
    0.73
     ब्रेकडाउन
    0.72
     Popcorn
    0.72
    OGND
    0.72
     Italijani
    0.70
    RenderAtEndOf
    0.70
     popcorn
    0.69
    Popcorn
    0.69
    Act Density 0.050%

    No Known Activations