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

    Neuronpedia

    INDEX
    Explanations

    to connect, to watch, to lean

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awasan
    0.40
     $$\
    0.40
     Informat
    0.39
     I
    0.38
     sayings
    0.38
     दिर
    0.38
    ewa
    0.38
     Lan
    0.37
     Ass
    0.36
     fakta
    0.36
    POSITIVE LOGITS
    が入
    0.45
     місто
    0.43
    fecture
    0.43
    വരുടെ
    0.38
    ডেল
    0.37
     இடம்பெ
    0.37
     বেড়ে
    0.36
    valent
    0.36
    மரு
    0.36
    に入れる
    0.36
    Act Density 0.000%

    No Known Activations