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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _choice
    -0.08
    plot
    -0.07
     magazine
    -0.06
    Exercise
    -0.06
    provider
    -0.06
    198
    -0.06
    =c
    -0.06
     ارزیابی
    -0.06
     positive
    -0.06
    Iterations
    -0.06
    POSITIVE LOGITS
     timedelta
    0.06
     ilma
    0.06
     follic
    0.06
     Achilles
    0.06
     бел
    0.06
     dod
    0.06
     Dial
    0.06
     Vimeo
    0.06
    ротив
    0.05
     DPR
    0.05
    Act Density 0.025%

    No Known Activations