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

    Neuronpedia

    INDEX
    Explanations

    npm start

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     placent
    0.87
    ским
    0.70
     વ્યવ
    0.70
    handlungen
    0.70
     working
    0.70
     execution
    0.69
    าน
    0.68
    meat
    0.67
     security
    0.67
     μο
    0.67
    POSITIVE LOGITS
    มากๆ
    0.63
     tanı
    0.61
    ぢ
    0.61
    인더
    0.59
    Rachel
    0.59
     fotoğraf
    0.59
     laiss
    0.58
     نخست
    0.57
    groomed
    0.57
     आर
    0.56
    Act Density 0.004%

    No Known Activations