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

    Neuronpedia

    INDEX
    Explanations

    Sunni

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    储备
    -0.08
     Zoo
    -0.08
    抑え
    -0.08
    ☓
    -0.07
    雨水
    -0.07
    .super
    -0.07
    erva
    -0.06
     ApiException
    -0.06
     bout
    -0.06
    锳
    -0.06
    POSITIVE LOGITS
     trackers
    0.07
     NgModule
    0.07
     Pornhub
    0.07
     Width
    0.07
    危
    0.07
    	de
    0.07
     CAUSED
    0.07
    MOST
    0.06
     GIF
    0.06
    거나
    0.06
    Act Density 0.001%

    No Known Activations