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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" in various contexts

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

    states of change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    operand
    -0.40
     Fische
    -0.40
    AppData
    -0.37
    muñeca
    -0.36
    guantes
    -0.36
     Wissenschaft
    -0.36
    Únete
    -0.36
    krä
    -0.36
    Saluti
    -0.36
     inventors
    -0.36
    POSITIVE LOGITS
    хьтан
    0.66
     started
    0.60
     begun
    0.60
     onAnimation
    0.56
     ended
    0.56
    :✨
    0.55
    started
    0.53
    migrationBuilder
    0.51
     censiti
    0.49
     시작
    0.47
    Act Density 0.092%

    No Known Activations