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
     foes
    -0.06
     overlap
    -0.06
    #af
    -0.06
    _categorical
    -0.06
     ван
    -0.06
    ём
    -0.06
    .backends
    -0.06
     pictured
    -0.06
     nargs
    -0.06
    faq
    -0.05
    POSITIVE LOGITS
     spice
    0.08
    _PID
    0.07
     Soda
    0.07
    money
    0.07
     Σα
    0.06
    杀
    0.06
    decision
    0.06
    芳
    0.06
     asym
    0.06
    profit
    0.06
    Act Density 0.001%

    No Known Activations