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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and expressions

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

    bit operations and shifts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zvuky
    -0.49
    principalColumn
    -0.48
     Segurança
    -0.48
     Garantía
    -0.48
     Italij
    -0.48
     psicología
    -0.47
     hırka
    -0.46
    guiente
    -0.45
     conmigo
    -0.45
     Мексичка
    -0.45
    POSITIVE LOGITS
     binary
    0.55
     powers
    0.53
     bit
    0.53
    Mask
    0.51
     Shift
    0.50
     shifts
    0.50
    Shift
    0.50
    Flags
    0.50
     mask
    0.48
     shift
    0.48
    Act Density 0.327%

    No Known Activations