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

    Neuronpedia

    INDEX
    Explanations

    expressions of disappointment or reflection on unfulfilled expectations

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

    negations and qualifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikiseite
    -0.57
    MigrationBuilder
    -0.54
    цездатний
    -0.45
    fortawesome
    -0.45
    RegressionTest
    -0.45
     Dirig
    -0.41
    ReusableCell
    -0.41
    ⤹
    -0.41
    beeren
    -0.40
     supr
    -0.40
    POSITIVE LOGITS
    fjspx
    0.59
     Paglinawan
    0.44
     Chwiliwch
    0.41
     nahilalakip
    0.40
     auroit
    0.40
    focusable
    0.40
    TouchListener
    0.40
    rational
    0.40
    llavero
    0.39
    ConstraintMaker
    0.39
    Act Density 0.062%

    No Known Activations