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

    Neuronpedia

    INDEX
    Explanations

    technical terms and unicode

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DR
    0.43
    Sports
    0.40
     ك
    0.39
     Hans
    0.39
    Greetings
    0.39
    etsk
    0.38
     ذ
    0.38
    ْ
    0.38
     Michael
    0.37
    otyping
    0.37
    POSITIVE LOGITS
     bluetooth
    0.49
     longiore
    0.46
    ೇವಿನ
    0.46
    絹
    0.45
    ྥ
    0.45
     multitud
    0.44
     शुर
    0.44
    巴士
    0.44
    નુ
    0.44
     phosphatase
    0.43
    Act Density 0.001%

    No Known Activations