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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reinforced
    -0.08
    それを
    -0.07
    Ồ
    -0.07
    coupon
    -0.07
    ്�
    -0.07
     ISIS
    -0.07
    hower
    -0.06
    ո
    -0.06
     docker
    -0.06
    סי
    -0.06
    POSITIVE LOGITS
    .presenter
    0.07
    .When
    0.07
    摩擦
    0.07
    .Nodes
    0.07
     date
    0.06
    ㈼
    0.06
    �
    0.06
    Medium
    0.06
    ух
    0.06
    婉
    0.06
    Act Density 0.000%

    No Known Activations