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

    Neuronpedia

    INDEX
    Explanations

    Phase change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    であ
    -0.08
     黑
    -0.07
     bleak
    -0.06
     důsled
    -0.06
     doorstep
    -0.06
    Tim
    -0.06
    (interface
    -0.06
     �
    -0.06
    _Al
    -0.06
    Wal
    -0.06
    POSITIVE LOGITS
     dissolved
    0.07
    Unsupported
    0.07
     player
    0.06
    pecified
    0.06
    uint
    0.06
    なく
    0.06
    0.06
    nicos
    0.06
     LEVEL
    0.06
    	kfree
    0.06
    Act Density 0.017%

    No Known Activations