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

    Neuronpedia

    INDEX
    Explanations

    XML code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .bz
    -0.07
     Bootstrap
    -0.07
    ίνη
    -0.07
     DESCRIPTION
    -0.07
    imits
    -0.07
    .xxx
    -0.06
    _ld
    -0.06
    edido
    -0.06
    оступ
    -0.06
    _FAILURE
    -0.06
    POSITIVE LOGITS
    /car
    0.06
     ）↵
    0.06
    &
    0.06
    FINITE
    0.06
     Sofa
    0.06
     [&](
    0.06
    __(↵
    0.06
    policy
    0.06
    ))):↵
    0.06
     Mutual
    0.06
    Act Density 0.016%

    No Known Activations