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

    Neuronpedia

    INDEX
    Explanations

    these + noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ра
    0.66
     Massacre
    0.66
    海外
    0.64
    是
    0.62
    Rachel
    0.61
    甲
    0.61
     Dentist
    0.59
    ulse
    0.59
     तलाक
    0.59
    Fantasy
    0.59
    POSITIVE LOGITS
    (${
    0.64
     environment
    0.63
    वायरमेंट
    0.62
     daimyo
    0.57
     relev
    0.56
     모습
    0.56
    \".
    0.56
     environnement
    0.54
     \"%
    0.54
     (${
    0.53
    Act Density 0.202%

    No Known Activations