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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     belongs
    -0.06
     alternating
    -0.06
     lành
    -0.06
    leftrightarrow
    -0.06
     suggestions
    -0.06
     yacc
    -0.06
     porch
    -0.06
    ль
    -0.06
     reproduction
    -0.06
    	boost
    -0.06
    POSITIVE LOGITS
    >About
    0.08
     ↵  ↵
    0.07
     druhé
    0.07
    bots
    0.07
    AppBar
    0.06
     trovare
    0.06
     Mos
    0.06
     ])↵↵
    0.06
    ｜
    0.06
     [|
    0.06
    Act Density 0.225%

    No Known Activations