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

    Neuronpedia

    INDEX
    Explanations

    apprenticeship or learning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    umi
    -0.08
    火车
    -0.08
    活力
    -0.07
    乘客
    -0.07
    矾
    -0.07
    -badge
    -0.07
    ވ
    -0.07
    ניגוד
    -0.07
     While
    -0.07
     pilgr
    -0.07
    POSITIVE LOGITS
    سلوك
    0.07
    Plans
    0.07
    EP
    0.07
    LAT
    0.07
    �
    0.07
    別の
    0.06
     Set
    0.06
    GOP
    0.06
    ...↵↵↵↵
    0.06
    Produ
    0.06
    Act Density 0.040%

    No Known Activations