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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ######↵
    -0.08
     burning
    -0.07
    buz
    -0.07
    rete
    -0.06
    _ng
    -0.06
     closes
    -0.06
    šlo
    -0.06
    .train
    -0.06
     Ví
    -0.06
    Issue
    -0.06
    POSITIVE LOGITS
    essenger
    0.06
     supplied
    0.06
     abilities
    0.06
     ass
    0.06
     гориз
    0.06
    (coeffs
    0.06
    .example
    0.06
    ))?
    0.06
     deletion
    0.06
     vorhand
    0.05
    Act Density 0.000%

    No Known Activations