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

    Neuronpedia

    INDEX
    Explanations

    crate rate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sigma
    -0.06
    	web
    -0.06
    units
    -0.06
    _hours
    -0.06
    าคา
    -0.06
    localized
    -0.06
     amb
    -0.06
    istribution
    -0.06
    Howard
    -0.06
    %");↵
    -0.06
    POSITIVE LOGITS
    rat
    0.08
     Brewers
    0.07
    TON
    0.07
     bracket
    0.07
     Spray
    0.07
     unc
    0.07
     fray
    0.07
     Det
    0.07
    χε
    0.07
     rost
    0.06
    Act Density 0.001%

    No Known Activations