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

    Neuronpedia

    INDEX
    Explanations

    rising quickly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     돈
    -0.07
     Edwards
    -0.06
    Guy
    -0.06
     Parks
    -0.06
     Rogers
    -0.06
     captivity
    -0.06
    Friday
    -0.06
    	size
    -0.06
     understands
    -0.06
     Nashville
    -0.06
    POSITIVE LOGITS
    "]=
    0.07
     FI
    0.07
    �
    0.07
    _##
    0.07
     commodo
    0.07
     POSSIBILITY
    0.06
    retweeted
    0.06
    .ManyToMany
    0.06
     především
    0.06
    eum
    0.06
    Act Density 0.038%

    No Known Activations