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

    Neuronpedia

    INDEX
    Explanations

    similes and comparisons

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

    similes using "like a"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sendStatus
    -0.33
     acrí
    -0.30
    UnusedPrivate
    -0.29
     viņ
    -0.29
    cl
    -0.29
     hozzá
    -0.28
     encarga
    -0.28
     menyer
    -0.26
     unknownFields
    -0.26
    ar
    -0.26
    POSITIVE LOGITS
     dieſer
    0.71
     dieſes
    0.70
    <pad>
    0.69
    <unused17>
    0.69
    <unused52>
    0.69
    <unused68>
    0.69
    <unused51>
    0.69
    <unused41>
    0.69
    <unused23>
    0.69
    <unused28>
    0.69
    Act Density 0.033%

    No Known Activations