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

    Neuronpedia

    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ?option
    -0.06
    AJOR
    -0.06
    ucson
    -0.06
    Hundreds
    -0.06
     khoán
    -0.06
    onya
    -0.06
    Acknowled
    -0.05
     EMS
    -0.05
    <(),
    -0.05
    tring
    -0.05
    POSITIVE LOGITS
     Sinn
    0.07
     Aux
    0.07
    >')↵
    0.07
     Grü
    0.07
    .head
    0.07
     Desc
    0.07
     sû
    0.07
    istant
    0.06
     case
    0.06
    อาร
    0.06
    Act Density 0.011%

    No Known Activations