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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Phone
    -0.06
     unexpectedly
    -0.06
    ificaciones
    -0.06
    句话
    -0.06
    river
    -0.06
     deed
    -0.06
     polynomial
    -0.06
     dijo
    -0.06
    .Channel
    -0.06
    _band
    -0.06
    POSITIVE LOGITS
     ها
    0.07
    _fac
    0.06
     intel
    0.06
    _rp
    0.06
    [ID
    0.06
    	br
    0.06
     tra
    0.06
     passé
    0.06
    itta
    0.06
     전에
    0.06
    Act Density 0.013%

    No Known Activations