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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or variables in scientific contexts

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

    mathematical series and physics notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ::$_
    -0.62
     resourceCulture
    -0.59
    OGND
    -0.52
    principalTable
    -0.49
    ]='\
    -0.46
     Bí
    -0.46
     Bany
    -0.46
     intentional
    -0.46
    queryInterface
    -0.45
     yyl
    -0.45
    POSITIVE LOGITS
     RELATIONS
    0.59
    Relations
    0.58
    AxisAlignment
    0.57
    ModelSerializer
    0.54
    Superview
    0.54
    atrician
    0.53
    })));
    0.52
     huyền
    0.52
     étrang
    0.52
     للمعارف
    0.52
    Act Density 0.530%

    No Known Activations