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

    Neuronpedia

    INDEX
    Explanations

    future human category

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Adobe
    0.55
    員
    0.52
    Colors
    0.51
    Ц
    0.51
    Cô
    0.48
    ai
    0.47
    Mud
    0.46
    Blue
    0.46
    Garden
    0.46
    Ｈ
    0.46
    POSITIVE LOGITS
     dawned
    0.54
     decompression
    0.50
     nutmeg
    0.49
    χύ
    0.48
     sinusoidal
    0.46
     towed
    0.46
     hibernation
    0.46
     zej
    0.46
     brutal
    0.46
     neuropathy
    0.46
    Act Density 0.001%

    No Known Activations