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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     discriminator
    -0.07
     технолог
    -0.07
    ağı
    -0.07
     bied
    -0.07
    ắc
    -0.07
    �
    -0.07
    _mag
    -0.06
     tích
    -0.06
    Gatt
    -0.06
    clair
    -0.06
    POSITIVE LOGITS
    RuntimeException
    0.06
    *
↵
    0.06
    .review
    0.06
    !!↵
    0.06
    Apply
    0.06
    Test
    0.05
    idle
    0.05
    .not
    0.05
     ////
    0.05
    Timeout
    0.05
    Act Density 0.012%

    No Known Activations