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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     microbi
    -0.07
     compared
    -0.06
     Author
    -0.06
     Prof
    -0.06
    -centered
    -0.06
     melodies
    -0.06
    ames
    -0.06
    …………………………………………
    -0.06
     Toshiba
    -0.06
     Organization
    -0.06
    POSITIVE LOGITS
    dart
    0.07
    (ip
    0.06
    steam
    0.06
    -fetch
    0.06
     اين
    0.06
    ..↵
    0.06
    ็บ
    0.06
    _MAIN
    0.06
    rates
    0.06
    .sequence
    0.06
    Act Density 0.071%

    No Known Activations