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

    Neuronpedia

    INDEX
    Explanations

    references to products and their descriptions

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

    new product

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Източници
    -0.60
    IVEREF
    -0.59
    лтемелер
    -0.58
    ViewInit
    -0.52
    Дереккөздер
    -0.52
    dotenv
    -0.52
     препратки
    -0.52
    ViewImports
    -0.51
     AppCompatTheme
    -0.50
     باخ
    -0.50
    POSITIVE LOGITS
     including
    0.38
     včetně
    0.37
     preuves
    0.37
     meubles
    0.37
     izquier
    0.34
     annat
    0.33
     grandeza
    0.33
     igreja
    0.33
    quiagem
    0.32
     andet
    0.32
    Act Density 0.213%

    No Known Activations