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

    Neuronpedia

    INDEX
    Explanations

    green

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LOAD
    -0.07
    される
    -0.07
    られる
    -0.07
     xác
    -0.06
     observations
    -0.06
     suchen
    -0.06
     거의
    -0.06
    _ray
    -0.06
    .getX
    -0.06
    .outputs
    -0.06
    POSITIVE LOGITS
     Verd
    0.07
    Paused
    0.06
    [U
    0.06
     Dough
    0.06
    -reset
    0.06
     farther
    0.06
    ॉप
    0.06
    �
    0.06
    Registr
    0.06
     narr
    0.06
    Act Density 0.012%

    No Known Activations