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

    Neuronpedia

    INDEX
    Explanations

    bias and applied

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resulted
    0.41
    Tile
    0.40
     виду
    0.40
    Tunnel
    0.40
    Tuple
    0.38
    بسم
    0.38
    Name
    0.37
    >"
    0.37
    ನಾಟಕ
    0.37
     بيان
    0.36
    POSITIVE LOGITS
    天気
    0.40
     miz
    0.39
     JCV
    0.39
    धनों
    0.38
     migr
    0.38
     mej
    0.38
     கெல்வின்
    0.38
     plek
    0.37
     cappuccino
    0.37
    hoven
    0.37
    Act Density 0.026%

    No Known Activations