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

    Neuronpedia

    INDEX
    Explanations

    et

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ATIO
    -0.06
    -$
    -0.06
    ‌ترین
    -0.06
    Dic
    -0.06
    _idxs
    -0.06
    reserve
    -0.06
    ба
    -0.06
     Incre
    -0.06
     Shak
    -0.06
    ху
    -0.06
    POSITIVE LOGITS
     et
    0.14
     hommes
    0.08
    .Bind
    0.07
     handle
    0.07
     Et
    0.06
     opt
    0.06
    улю
    0.06
     justified
    0.06
    Errors
    0.06
    ,map
    0.06
    Act Density 0.003%

    No Known Activations