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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their relationships in mathematical contexts

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

    math equations with variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     embaj
    -0.49
     Moscú
    -0.48
     féminin
    -0.41
     libremente
    -0.37
     invitado
    -0.37
     leçons
    -0.37
     bahía
    -0.37
     movilidad
    -0.37
     bienvenue
    -0.36
     caminos
    -0.36
    POSITIVE LOGITS
    ArgumentParser
    0.72
    InputBorder
    0.69
     CreateTagHelper
    0.68
    Aholisi
    0.67
    ContentLoaded
    0.66
    MemoryWarning
    0.66
    RectangleBorder
    0.62
     MainAxisSize
    0.62
    Autoritní
    0.60
    ⟬
    0.57
    Act Density 0.066%

    No Known Activations