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

    Neuronpedia

    INDEX
    Explanations

    careers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    يج
    -0.06
    oner
    -0.06
     TX
    -0.06
    ø
    -0.06
     Dut
    -0.06
     appliances
    -0.06
     stimuli
    -0.06
    	md
    -0.06
    daughter
    -0.06
    —that
    -0.06
    POSITIVE LOGITS
     phận
    0.07
    âm
    0.06
    325
    0.06
    tridge
    0.06
    ChangeEvent
    0.06
     방법
    0.06
     Jelly
    0.06
    (edges
    0.06
    owering
    0.06
     заболевания
    0.06
    Act Density 0.017%

    No Known Activations