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

    Neuronpedia

    INDEX
    Explanations

    phrases related to self-reflection and personal growth

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

    Beginning of sentences

    np_acts-logits-general · gemini-2.0-flash

    introducing clauses or reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     recientemente
    -0.40
     recentemente
    -0.35
     пользователем
    -0.34
     gering
    -0.34
     Ausführungen
    -0.31
    RegressionTest
    -0.30
     Autorizaciones
    -0.29
     xinh
    -0.29
     wykonania
    -0.29
     olvides
    -0.29
    POSITIVE LOGITS
    ьаж
    0.59
     Chwiliwch
    0.58
    GraphicsUnit
    0.58
    bkz
    0.56
    migrationBuilder
    0.56
     للاسماء
    0.54
     Theſe
    0.53
    Hozzáférés
    0.52
     utafitiHapana
    0.52
    swar
    0.50
    Act Density 0.292%

    No Known Activations