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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Login
    -0.07
    �
    -0.07
    _syntax
    -0.07
    iness
    -0.06
    tte
    -0.06
    [table
    -0.06
    �
    -0.06
    商量
    -0.06
    工夫
    -0.06
     Thumbnails
    -0.06
    POSITIVE LOGITS
     sentinel
    0.08
    .selector
    0.06
    댄
    0.06
     جميل
    0.06
    ８
    0.06
    甦
    0.06
    对抗
    0.06
    :f
    0.06
    独角
    0.06
    を与
    0.06
    Act Density 0.002%

    No Known Activations