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

    Neuronpedia

    INDEX
    Explanations

    Linear algebra/matrices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reigning
    -0.09
     fascination
    -0.07
     Harper
    -0.07
    Activity
    -0.07
    Leaves
    -0.07
     unmanaged
    -0.07
    .Theme
    -0.07
     Dad
    -0.07
     overst
    -0.07
    .Dom
    -0.07
    POSITIVE LOGITS
     RHS
    0.09
     ವಿಭಾಗ
    0.09
     сумма
    0.09
     иди
    0.09
     alu
    0.09
     методом
    0.08
     НА
    0.08
     aline
    0.08
    _rhs
    0.08
     ಮುಖ್ಯ
    0.08
    Act Density 0.012%

    No Known Activations