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

    Neuronpedia

    INDEX
    Explanations

    security

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spos
    -0.07
    	t
    -0.06
     HOUSE
    -0.06
    feb
    -0.06
    gst
    -0.06
     ह
    -0.06
    [Byte
    -0.06
     touched
    -0.06
     Patreon
    -0.06
     essay
    -0.06
    POSITIVE LOGITS
     Norton
    0.07
     security
    0.07
     stability
    0.07
     tecn
    0.07
     contentType
    0.06
     setw
    0.06
     bytearray
    0.06
     KeyboardInterrupt
    0.06
    협
    0.06
    _SUPER
    0.06
    Act Density 0.008%

    No Known Activations