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

    Neuronpedia

    INDEX
    Explanations

    roc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (dtype
    -0.07
    �
    -0.07
     isl
    -0.06
     Omar
    -0.06
     depot
    -0.06
    oted
    -0.06
     enumer
    -0.06
     pasta
    -0.06
    detect
    -0.06
     nag
    -0.06
    POSITIVE LOGITS
     scri
    0.07
     recipro
    0.07
     muschi
    0.07
     wah
    0.07
     yıllık
    0.07
     göl
    0.07
    Offers
    0.07
     相
    0.06
     gioc
    0.06
    NoArgsConstructor
    0.06
    Act Density 0.004%

    No Known Activations