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

    Neuronpedia

    INDEX
    Explanations

    math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    انع
    -0.09
     جهان
    -0.08
     لازم
    -0.08
     prototypes
    -0.08
     सहज
    -0.07
     conservation
    -0.07
    שר
    -0.07
    ทาง
    -0.07
    ुकूल
    -0.07
     स्वतंत्र
    -0.07
    POSITIVE LOGITS
     peter
    0.08
     noa
    0.08
     Oktober
    0.07
     SUM
    0.07
     nin
    0.07
     continues
    0.07
     Williamsburg
    0.07
     granddaughter
    0.07
     muddy
    0.07
     dimin
    0.07
    Act Density 0.040%

    No Known Activations