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

    Neuronpedia

    INDEX
    Explanations

    Utility bills and meters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Klan
    -0.08
    🥶
    -0.07
     çocukların
    -0.07
     onde
    -0.07
    第二批
    -0.07
    ᠨ
    -0.07
    游击
    -0.07
     thirds
    -0.06
    减值
    -0.06
     возд
    -0.06
    POSITIVE LOGITS
     figuring
    0.07
     empowered
    0.07
    .dialog
    0.07
     confronted
    0.07
    ause
    0.07
    -source
    0.07
    Model
    0.07
    -block
    0.06
    未成
    0.06
     paul
    0.06
    Act Density 0.030%

    No Known Activations