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

    Neuronpedia

    INDEX
    Explanations

    Arg

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ạo
    -0.07
    िछल
    -0.07
     militar
    -0.06
    esidir
    -0.06
     libro
    -0.06
     unheard
    -0.06
    );$
    -0.06
     neměl
    -0.06
     *</
    -0.06
    Mensaje
    -0.06
    POSITIVE LOGITS
     compartment
    0.07
    _listing
    0.06
     compartments
    0.06
     gerçek
    0.06
     diff
    0.06
    .Iter
    0.06
     noises
    0.06
    colour
    0.06
    _index
    0.06
     mass
    0.06
    Act Density 0.002%

    No Known Activations