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

    Neuronpedia

    INDEX
    Explanations

    SDKs and APIs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     painted
    0.27
    innie
    0.26
     any
    0.25
     Harvard
    0.24
     stained
    0.23
     Mighty
    0.23
    ibley
    0.23
    ecause
    0.23
     American
    0.23
     ivory
    0.23
    POSITIVE LOGITS
    クラウド
    0.38
     sdk
    0.38
     SDK
    0.37
     앱
    0.35
     api
    0.34
    Cloud
    0.33
    SDK
    0.33
     OpenAPI
    0.32
    sdk
    0.32
     플랫폼
    0.32
    Act Density 0.011%

    No Known Activations