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

    Neuronpedia

    INDEX
    Explanations

    everything is made of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mentoring
    0.49
     infertility
    0.44
     mentorship
    0.43
    ನ್ನೆ
    0.42
    algebra
    0.41
    behavior
    0.39
     অল্প
    0.38
    MYSQL
    0.38
    므
    0.37
    stress
    0.37
    POSITIVE LOGITS
     Geräte
    0.45
     جهاز
    0.45
     urządzenia
    0.44
     houses
    0.42
     urząd
    0.41
     napraw
    0.41
    汽车
    0.40
     Devices
    0.40
     उपकरण
    0.40
     possesses
    0.39
    Act Density 0.001%

    No Known Activations