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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    压力
    -0.08
     sophist
    -0.07
    rying
    -0.07
     shrinking
    -0.07
     disf
    -0.07
    脚
    -0.07
    も
    -0.07
     Andy
    -0.07
     confined
    -0.07
     пресс
    -0.07
    POSITIVE LOGITS
    ങ്ങനെ
    0.09
     എല്ലാ
    0.09
     các
    0.08
     օ
    0.08
     വിവിധ
    0.08
     उन
    0.08
     కొన్ని
    0.08
     അവ
    0.08
     മറ്റ്
    0.08
     ndị
    0.08
    Act Density 0.004%

    No Known Activations