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

    Neuronpedia

    INDEX
    Explanations

    references to examples or lists in various contexts

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

    introducing examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.50
     betweenstory
    -0.48
    migrationBuilder
    -0.44
    Composable
    -0.43
    HasMaxLength
    -0.43
    spreis
    -0.42
    FunctionFlags
    -0.42
    blech
    -0.41
    GOTREF
    -0.40
     useParams
    -0.40
    POSITIVE LOGITS
     propOrder
    0.50
    包括
    0.44
     including
    0.41
     muun
    0.41
    ::{
    0.40
    EndInit
    0.40
    TagMode
    0.39
    including
    0.38
     خارجية
    0.38
    uding
    0.36
    Act Density 0.043%

    No Known Activations