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

    Neuronpedia

    INDEX
    Explanations

    common words like "the", "that", "this", "our", "their", etc

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    featureID
    -0.57
    záll
    -0.56
     indeed
    -0.55
    matchCondition
    -0.54
    rather
    -0.54
     sagen
    -0.54
     Höchst
    -0.53
    arschijnlijk
    -0.52
    istor
    -0.52
    }])
    -0.52
    POSITIVE LOGITS
    ंदीखरीदारी
    0.50
     році
    0.49
    fhir
    0.47
    RenderAtEndOf
    0.46
    çados
    0.46
    0.46
    PIA
    0.45
     utafitiHapana
    0.45
     pertence
    0.43
     ModelExpression
    0.43
    Act Density 4.558%

    No Known Activations