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

    Neuronpedia

    INDEX
    Explanations

    english language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parole
    -0.07
    луата
    -0.06
     ．
    -0.06
     practical
    -0.06
    最初
    -0.06
    According
    -0.06
     mating
    -0.06
     alerted
    -0.06
     dass
    -0.06
     Cas
    -0.06
    POSITIVE LOGITS
    EEE
    0.07
    ผม
    0.07
     họ
    0.07
    �
    0.06
    들이
    0.06
    เข
    0.06
     저
    0.06
    *this
    0.06
    ilha
    0.06
     soit
    0.06
    Act Density 0.304%

    No Known Activations