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

    Neuronpedia

    INDEX
    Explanations

    arithmetic expressions involving addition operations

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

    addition and offset operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    %)$
    -0.55
     surla
    -0.49
    )}_{
    -0.49
     ?>>
    -0.47
    ennio
    -0.45
    ″]
    -0.45
    ])))
    -0.44
    ]$}
    -0.43
    able
    -0.43
    ROC
    -0.43
    POSITIVE LOGITS
     +
    0.90
     +=
    0.82
     $+\
    0.76
    +\
    0.71
     $+
    0.70
    ()+
    0.69
    +(
    0.69
     +(
    0.68
    )+(
    0.68
     +
    0.66
    Act Density 0.062%

    No Known Activations