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

    Neuronpedia

    INDEX
    Explanations

    instances of emotional reactions or states expressed in the text

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

    corrupt people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Brainz
    -0.49
    PCell
    -0.48
     Normdatei
    -0.37
     Pennington
    -0.37
     ſta
    -0.37
    Mam
    -0.36
     rik
    -0.36
    migrationBuilder
    -0.36
     Nar
    -0.36
     directo
    -0.35
    POSITIVE LOGITS
    thenReturn
    0.41
     dignité
    0.40
    商品説明
    0.38
    extAlignment
    0.38
    UnknownFieldSet
    0.38
    yamaha
    0.38
    MethodManager
    0.37
    outchouc
    0.36
     unknownFields
    0.36
    AccessorTable
    0.36
    Act Density 0.068%

    No Known Activations