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

    Neuronpedia

    INDEX
    Explanations

    approach

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Expenses
    -0.07
    ْت
    -0.06
     Nord
    -0.06
     Lic
    -0.06
    ******/↵
    -0.06
    年代
    -0.06
     Lay
    -0.06
     púb
    -0.06
     ordin
    -0.06
    MMMM
    -0.06
    POSITIVE LOGITS
     Morton
    0.07
    _Generic
    0.06
     Sergei
    0.06
    hcp
    0.06
     eles
    0.06
    _SELF
    0.06
    _IDLE
    0.06
    ueblo
    0.06
    elsea
    0.06
    ack
    0.06
    Act Density 0.013%

    No Known Activations