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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hey
    -0.07
     letzten
    -0.06
    、それ
    -0.06
     además
    -0.06
     bleak
    -0.06
    .ComboBox
    -0.06
    Ready
    -0.06
    However
    -0.06
    楽
    -0.06
     achievements
    -0.06
    POSITIVE LOGITS
    .engine
    0.07
    ubble
    0.06
     ''),
    0.06
    别
    0.06
    jax
    0.06
     PŘ
    0.06
    ertoire
    0.06
     terrestrial
    0.06
     ロ
    0.06
    neh
    0.06
    Act Density 0.094%

    No Known Activations