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

    Neuronpedia

    INDEX
    Explanations

    Discourse markers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    outputs
    -0.07
     ix
    -0.07
     detailing
    -0.07
    烝
    -0.07
     //----------------------------------------------------------------
    -0.07
     الذين
    -0.07
    //-----------------------------------------------------------------------------↵
    -0.06
    ackers
    -0.06
    甚至还
    -0.06
    そも
    -0.06
    POSITIVE LOGITS
    >b
    0.07
    isseur
    0.07
    unist
    0.07
    (N
    0.07
    哈哈哈
    0.07
     physique
    0.07
    aron
    0.07
    ﮟ
    0.07
    𝒹
    0.07
    帚
    0.07
    Act Density 0.040%

    No Known Activations