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

    Neuronpedia

    INDEX
    Explanations

    mathematical theorems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    แนะ
    -0.07
     derivative
    -0.07
     give
    -0.07
     giver
    -0.06
    -reviewed
    -0.06
     gave
    -0.06
     derivatives
    -0.06
     conveyed
    -0.06
     �
    -0.06
     absorption
    -0.06
    POSITIVE LOGITS
    -users
    0.06
    =%.
    0.06
     Searches
    0.06
     البي
    0.06
     다양한
    0.06
    __',
    0.06
    _HAND
    0.06
     па
    0.06
     Generator
    0.06
    .bank
    0.06
    Act Density 0.023%

    No Known Activations