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

    Neuronpedia

    INDEX
    Explanations

    haven

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ンチ
    -0.06
    ávky
    -0.06
     applicant
    -0.06
     arbitrary
    -0.06
    ject
    -0.06
    GD
    -0.06
     nozzle
    -0.06
    .output
    -0.06
     randomly
    -0.05
     aeros
    -0.05
    POSITIVE LOGITS
    obierno
    0.07
    _scroll
    0.06
     phim
    0.06
    işi
    0.06
    罚
    0.06
    Liv
    0.06
     meat
    0.06
     yapım
    0.06
     Santiago
    0.06
    落ち
    0.06
    Act Density 0.041%

    No Known Activations