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

    Neuronpedia

    INDEX
    Explanations

    legal motions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tyler
    -0.07
     Merge
    -0.07
    INavigationController
    -0.07
    混合
    -0.07
    PLETED
    -0.06
    屆
    -0.06
     Vice
    -0.06
    	from
    -0.06
    Alternative
    -0.06
     FI
    -0.06
    POSITIVE LOGITS
     dash
    0.08
    庄
    0.07
     slopes
    0.06
    osex
    0.06
     rounding
    0.06
    نین
    0.06
    (`↵
    0.06
    buat
    0.06
     multic
    0.06
    bett
    0.06
    Act Density 0.016%

    No Known Activations