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

    Neuronpedia

    INDEX
    Explanations

    OAuth applications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ağır
    -0.07
    と思い
    -0.07
    完结
    -0.06
     совсем
    -0.06
     hazırl
    -0.06
    ∉
    -0.06
    <title
    -0.06
    ้ำ
    -0.06
     diplomat
    -0.06
     alm
    -0.06
    POSITIVE LOGITS
    🔧
    0.07
     raised
    0.07
     dropped
    0.07
    -ret
    0.07
    会展
    0.07
    ция
    0.07
     hostile
    0.07
    lia
    0.07
    ulo
    0.07
    �
    0.06
    Act Density 0.012%

    No Known Activations