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

    Neuronpedia

    INDEX
    Explanations

    spouses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Response
    -0.08
    ournaments
    -0.07
     chemistry
    -0.07
     manufacture
    -0.07
    ஸ
    -0.07
    面向
    -0.07
    ensagem
    -0.06
     Fol
    -0.06
    apeutics
    -0.06
     bfs
    -0.06
    POSITIVE LOGITS
    =$((
    0.08
     mí
    0.07
     cru
    0.07
    ㉱
    0.07
    Suit
    0.06
    随手
    0.06
     vista
    0.06
    农户
    0.06
    	Dim
    0.06
    裛
    0.06
    Act Density 0.024%

    No Known Activations