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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (requestCode
    -0.08
     MainWindow
    -0.07
     unittest
    -0.07
    _empresa
    -0.07
     Attacks
    -0.07
    _SPELL
    -0.06
    _experiment
    -0.06
     Harrison
    -0.06
    (server
    -0.06
    	core
    -0.06
    POSITIVE LOGITS
     MMA
    0.06
     을
    0.06
    _datas
    0.06
     tarihli
    0.06
    となる
    0.06
    अब
    0.06
     hacer
    0.06
    ัศน
    0.06
    客
    0.06
    ausal
    0.06
    Act Density 0.025%

    No Known Activations