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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >}
    -0.09
     popul
    -0.08
     leuk
    -0.08
    ระดับ
    -0.07
     locales
    -0.07
    >}↵
    -0.07
     Island
    -0.07
     episod
    -0.07
     dak
    -0.07
    õ
    -0.07
    POSITIVE LOGITS
     optimization
    0.11
     maximizing
    0.10
     maximize
    0.10
     minimizing
    0.10
     minimize
    0.10
    Optimization
    0.10
     optimize
    0.09
     optimizing
    0.09
    Optimize
    0.09
     Optimization
    0.09
    Act Density 0.104%

    No Known Activations