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

    Neuronpedia

    INDEX
    Explanations

    Swedish place names

    oai_token-act-pair · gemini-2.0-flash

    Swedish prepositions

    np_token-act-pair-logits · gpt-4o-mini

    Swedish language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stället
    -1.02
     varandra
    -0.99
    writeFieldEnd
    -0.85
    AutoScaleMode
    -0.81
     photolibrary
    -0.78
     ModelExpression
    -0.78
     staden
    -0.75
     виправивши
    -0.75
     Shakspeare
    -0.75
    IsMutable
    -0.75
    POSITIVE LOGITS
     och
    0.62
     av
    0.60
     upp
    0.59
     ut
    0.56
     som
    0.56
     till
    0.56
     för
    0.56
     på
    0.55
     sk
    0.53
     med
    0.52
    Act Density 1.234%

    No Known Activations