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

    Neuronpedia

    INDEX
    Explanations

    Text from various sources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conducive
    -0.09
     aproxima
    -0.08
     barrier
    -0.08
    scheme
    -0.08
     simplified
    -0.08
     walkway
    -0.08
     nicely
    -0.07
    	form
    -0.07
     profession
    -0.07
     edgy
    -0.07
    POSITIVE LOGITS
    μι
    0.09
     unusually
    0.09
    Atlant
    0.08
     Atlantis
    0.08
     Siam
    0.08
     ungewöhn
    0.08
     Sich
    0.08
     Moon
    0.08
    σω
    0.08
     Neural
    0.08
    Act Density 0.053%

    No Known Activations