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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     babe
    -0.08
    	address
    -0.08
     irre
    -0.07
     elem
    -0.06
    IRCLE
    -0.06
     muchas
    -0.06
    _AREA
    -0.06
     celle
    -0.06
     caffeine
    -0.06
     aerobic
    -0.06
    POSITIVE LOGITS
     to
    0.13
     To
    0.12
    To
    0.10
     Cannot
    0.09
     TO
    0.09
    to
    0.09
    must
    0.08
    Cannot
    0.08
    TO
    0.08
     will
    0.08
    Act Density 0.802%

    No Known Activations