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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     μαζί
    -0.06
    Document
    -0.06
    рами
    -0.06
    ULATOR
    -0.06
    'ya
    -0.06
    ذا
    -0.06
     disgrace
    -0.06
    'na
    -0.06
     Kad
    -0.06
     vidéos
    -0.06
    POSITIVE LOGITS
    ционной
    0.06
    abajo
    0.06
     países
    0.06
     hem
    0.06
    .des
    0.06
    _unc
    0.06
    etermination
    0.06
    _Space
    0.06
     middle
    0.06
     habe
    0.06
    Act Density 0.002%

    No Known Activations