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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Election
    -0.08
     Executive
    -0.07
     Boss
    -0.07
     punish
    -0.07
     pres
    -0.07
    /tasks
    -0.07
     स
    -0.07
     brushing
    -0.06
    ジョ
    -0.06
    (instr
    -0.06
    POSITIVE LOGITS
     geral
    0.07
    واقع
    0.07
     ?',
    0.07
     등을
    0.07
     solidarity
    0.07
     endemic
    0.07
    〞
    0.07
     RuntimeError
    0.06
    外籍
    0.06
     DACA
    0.06
    Act Density 0.000%

    No Known Activations