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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving combinations and dependencies in a theoretical context

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

    combined operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.53
     OFDb
    -0.44
    RTEE
    -0.43
    moveToFirst
    -0.41
     zoude
    -0.40
    øya
    -0.40
    RRect
    -0.40
    spar
    -0.39
    morphosis
    -0.39
     تضيفلها
    -0.38
    POSITIVE LOGITS
     joint
    0.73
     combined
    0.71
     together
    0.68
    Together
    0.67
     Combined
    0.66
     Together
    0.65
    together
    0.65
     conjunta
    0.65
     juntos
    0.64
    Combined
    0.63
    Act Density 0.179%

    No Known Activations