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

    Neuronpedia

    INDEX
    Explanations

    references to professional titles and affiliations

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

    specific named entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AttributeSet
    -0.43
    Bakgrunnsstoff
    -0.40
    ps
    -0.36
    optionalTypeArgs
    -0.35
    HasIndex
    -0.35
    afficheront
    -0.35
    InSection
    -0.35
    ölker
    -0.34
    esez
    -0.34
    一下
    -0.34
    POSITIVE LOGITS
     ब्रेकडाउन
    0.61
     queſta
    0.56
    <unused8>
    0.56
    <unused28>
    0.56
    <unused3>
    0.56
    <pad>
    0.56
    <unused41>
    0.55
    <unused43>
    0.55
    <unused14>
    0.55
    [@BOS@]
    0.55
    Act Density 0.014%

    No Known Activations