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

    Neuronpedia

    INDEX
    Explanations

    Abstract concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .repository
    -0.07
     throws
    -0.07
    адки
    -0.07
    everything
    -0.07
     caring
    -0.06
    .Collectors
    -0.06
     recogn
    -0.06
    ходит
    -0.06
    这一
    -0.06
    dık
    -0.06
    POSITIVE LOGITS
    Aceptar
    0.06
    ματο
    0.06
    _LO
    0.06
     milliseconds
    0.06
     Access
    0.06
    butt
    0.06
    ایز
    0.06
    мента
    0.06
    แต
    0.06
    /pp
    0.06
    Act Density 0.084%

    No Known Activations