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

    Neuronpedia

    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MAL
    -0.07
     localize
    -0.07
     NBC
    -0.06
    佩
    -0.06
     lịch
    -0.06
     ugl
    -0.06
    pressure
    -0.06
    boBox
    -0.06
    	body
    -0.06
    Tracks
    -0.06
    POSITIVE LOGITS
    يات
    0.07
     rumours
    0.07
     Round
    0.06
    .Resume
    0.06
     मध
    0.06
    _EM
    0.06
    Only
    0.06
    â
    0.06
    ty
    0.06
     відбувається
    0.06
    Act Density 0.010%

    No Known Activations