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

    Neuronpedia

    INDEX
    Explanations

    risk and resource

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    alignParent
    1.16
    скільки
    1.12
     बुखार
    1.08
     IMC
    1.08
    Oxygen
    1.08
    DOI
    1.06
     stalemate
    1.05
    筋
    1.05
    estado
    1.04
     таком
    1.04
    POSITIVE LOGITS
    ک
    1.52
    뚤
    1.27
     coles
    1.25
     ações
    1.23
    𝘂
    1.20
    েশ
    1.20
     innan
    1.16
    𝗶
    1.14
    कार
    1.14
    ний
    1.13
    Act Density 0.000%

    No Known Activations