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

    Neuronpedia

    INDEX
    Explanations

    delimiter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    тів
    -0.07
    :red
    -0.06
    築
    -0.06
     Syntax
    -0.06
    ЕТ
    -0.06
    IDEOS
    -0.06
     propaganda
    -0.06
    [](
    -0.06
    *(
    -0.06
    otos
    -0.06
    POSITIVE LOGITS
    /Foundation
    0.07
     جنوب
    0.07
     Dump
    0.06
    roker
    0.06
    �
    0.06
     đào
    0.06
     accurate
    0.06
    τερη
    0.06
     Presenter
    0.06
    ilater
    0.06
    Act Density 0.004%

    No Known Activations