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

    Neuronpedia

    INDEX
    Explanations

    say profanity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     çalışan
    -0.07
    	cv
    -0.06
    irtual
    -0.06
     screwed
    -0.06
    tmp
    -0.06
     cortex
    -0.06
     neurons
    -0.06
    arm
    -0.06
     metros
    -0.06
     están
    -0.06
    POSITIVE LOGITS
    .ALIGN
    0.07
    egade
    0.07
     Blitz
    0.07
    .Article
    0.07
     prive
    0.06
    _Ent
    0.06
     Maritime
    0.06
    .Console
    0.06
     MILL
    0.06
    )init
    0.06
    Act Density 0.221%

    No Known Activations