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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quarantine
    -0.07
     tantr
    -0.07
     smo
    -0.06
     protože
    -0.06
    >();↵
    -0.06
    iro
    -0.06
    ويت
    -0.06
     пока
    -0.06
    kar
    -0.06
    	t
    -0.06
    POSITIVE LOGITS
     credit
    0.06
     '__
    0.06
    人が
    0.06
    _BTN
    0.06
     stages
    0.06
     QText
    0.06
    _references
    0.06
    ोद
    0.06
     wavelength
    0.06
    spd
    0.06
    Act Density 0.075%

    No Known Activations