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

    Neuronpedia

    INDEX
    Explanations

    math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .data
    -0.07
     мик
    -0.07
    파
    -0.07
     alma
    -0.06
    -child
    -0.06
    leine
    -0.06
    &a
    -0.06
     平
    -0.06
     Berk
    -0.06
     Audio
    -0.06
    POSITIVE LOGITS
    ائج
    0.07
    Personally
    0.07
     Rencontres
    0.07
    AFF
    0.07
    ้าห
    0.06
    >'
↵
    0.06
    swana
    0.06
    urret
    0.06
    iability
    0.06
    itler
    0.06
    Act Density 0.019%

    No Known Activations