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

    Neuronpedia

    INDEX
    Explanations

    single quote

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sữa
    -0.09
     müd
    -0.08
     smugg
    -0.08
     jumps
    -0.07
     handleMessage
    -0.07
     rapes
    -0.07
     defense
    -0.07
    Aligned
    -0.07
    噗
    -0.07
    网投
    -0.07
    POSITIVE LOGITS
    开工
    0.07
    淄博
    0.07
     Hil
    0.07
    -clear
    0.07
    实效
    0.07
     sal
    0.07
    주택
    0.07
    .DockStyle
    0.07
    $select
    0.06
     ako
    0.06
    Act Density 0.002%

    No Known Activations