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

    Neuronpedia

    INDEX
    Explanations

    bitwise operations and manipulation in code

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

    bitwise AND with M_

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.78
     Houſe
    -0.65
     ſche
    -0.64
     ſta
    -0.63
     myſelf
    -0.63
    ſelves
    -0.61
     ſtate
    -0.61
     Jefus
    -0.60
     themſelves
    -0.60
     houſe
    -0.59
    POSITIVE LOGITS
    Personendaten
    0.45
     isolato
    0.44
     &&
    0.44
     |=
    0.44
     &
    0.43
     ^=
    0.43
     asupra
    0.40
    GEBURTSDATUM
    0.40
     \&
    0.38
     &&
    0.37
    Act Density 0.017%

    No Known Activations