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

    Neuronpedia

    INDEX
    Explanations

    upcoming announcements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .co
    -0.06
    ([-
    -0.06
    µ
    -0.06
    	cur
    -0.06
    ้าก
    -0.06
    cw
    -0.06
    _clr
    -0.06
    640
    -0.06
     παρά
    -0.06
     Acrobat
    -0.06
    POSITIVE LOGITS
     BIT
    0.08
     ASD
    0.07
    ImGui
    0.06
     Lod
    0.06
    balances
    0.06
     dopamine
    0.06
     Hob
    0.06
     cherish
    0.06
     ries
    0.06
     게임
    0.06
    Act Density 0.041%

    No Known Activations