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

    Neuronpedia

    INDEX
    Explanations

    context or collaboration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     යු
    0.50
     ار
    0.49
    舉行
    0.49
    ជាតិ
    0.47
     modèles
    0.47
     කැ
    0.46
    Projekt
    0.46
     modello
    0.46
     ضمان
    0.45
     ውጤ
    0.45
    POSITIVE LOGITS
    с
    0.48
    ian
    0.47
    aiman
    0.46
     Collaborate
    0.46
     collab
    0.45
    ши
    0.45
    шава
    0.45
    rary
    0.44
    alaman
    0.44
    н
    0.43
    Act Density 0.001%

    No Known Activations