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

    Neuronpedia

    INDEX
    Explanations

    cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    trak
    -0.06
    áhl
    -0.06
    .eof
    -0.06
     deeds
    -0.06
     {}'.
    -0.06
    ='%
    -0.06
    )',
    -0.05
    ...\
    -0.05
     ""),↵
    -0.05
     東京
    -0.05
    POSITIVE LOGITS
    aravel
    0.07
     Phil
    0.07
     природ
    0.07
    	Vector
    0.07
     معل
    0.06
     Ан
    0.06
    (jPanel
    0.06
    เทศ
    0.06
     lawy
    0.06
    лаш
    0.06
    Act Density 0.000%

    No Known Activations