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

    Neuronpedia

    INDEX
    Explanations

    listening watching viewing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     தலைவர்
    -0.09
    იჩ
    -0.08
     Admissions
    -0.08
    იღ
    -0.08
     forbid
    -0.08
    atamente
    -0.08
    իճ
    -0.07
     ઘણ
    -0.07
    Hosts
    -0.07
    ოვანი
    -0.07
    POSITIVE LOGITS
    体验
    0.12
    享
    0.11
     enjoyment
    0.10
    楽し
    0.10
    观看
    0.10
    阅
    0.09
     viewing
    0.09
    安心
    0.09
    覚
    0.09
     strolling
    0.09
    Act Density 0.088%

    No Known Activations