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

    Neuronpedia

    INDEX
    Explanations

    iframe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     что
    -0.07
    ++]
    -0.07
     původ
    -0.06
     plight
    -0.06
     Reco
    -0.06
     transporte
    -0.06
     penn
    -0.06
     Bobby
    -0.06
     ]]↵
    -0.06
    ']}
    -0.06
    POSITIVE LOGITS
    /Instruction
    0.08
    .Scale
    0.07
    graphics
    0.07
     inhal
    0.06
     Bahrain
    0.06
     collaborate
    0.06
    引用
    0.06
    IMAGE
    0.06
    ＿＿＿＿＿＿＿＿
    0.06
    ابة
    0.06
    Act Density 0.003%

    No Known Activations