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

    Neuronpedia

    INDEX
    Explanations

    predictions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     เน
    -0.07
    ंच
    -0.07
     lj
    -0.07
     �
    -0.07
    Tracks
    -0.07
    ∧
    -0.06
    كه
    -0.06
    \modules
    -0.06
                     
    -0.06
    _finished
    -0.06
    POSITIVE LOGITS
     besoin
    0.07
    /ayushman
    0.06
    =models
    0.06
     Jeremiah
    0.06
     Abrams
    0.06
     memories
    0.06
    346
    0.06
    .Listen
    0.06
     indemn
    0.06
     milano
    0.06
    Act Density 0.004%

    No Known Activations