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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     punishments
    -0.06
     strengthened
    -0.06
     dolphin
    -0.06
     dispositivo
    -0.06
     Django
    -0.06
    ItemSelectedListener
    -0.06
    ANGO
    -0.06
     discuss
    -0.06
    lsruhe
    -0.06
     coastline
    -0.06
    POSITIVE LOGITS
     toh
    0.06
     filmer
    0.06
    ddie
    0.06
    одейств
    0.06
    тр
    0.06
    جی
    0.06
     otel
    0.06
    -analysis
    0.06
     finding
    0.06
     dc
    0.06
    Act Density 0.000%

    No Known Activations