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

    Neuronpedia

    INDEX
    Explanations

    mathematical reasoning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wahrscheinlich
    -0.08
     definitivo
    -0.08
    Since
    -0.08
     nicht
    -0.08
    Δεν
    -0.08
    ీఆర్
    -0.08
     spätestens
    -0.08
     posiblemente
    -0.08
     vermutlich
    -0.08
     האחרון
    -0.08
    POSITIVE LOGITS
     Suppose
    0.12
     suppose
    0.11
     مثلا
    0.10
     näiteks
    0.09
     hipot
    0.09
     Example
    0.09
     repente
    0.09
     accidentally
    0.09
     purposely
    0.08
    突然
    0.08
    Act Density 0.082%

    No Known Activations