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

    Neuronpedia

    INDEX
    Explanations

    google

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Technical
    -0.07
     conducive
    -0.07
     owes
    -0.06
     owe
    -0.06
     medium
    -0.06
    Fair
    -0.06
     Ant
    -0.06
     человечес
    -0.06
    Just
    -0.06
    Good
    -0.06
    POSITIVE LOGITS
    ENTE
    0.07
    deserialize
    0.07
     América
    0.07
     BIT
    0.07
     شاهد
    0.07
     проис
    0.07
     ninh
    0.07
    はない
    0.07
    )\<
    0.06
    beh
    0.06
    Act Density 0.020%

    No Known Activations