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

    Neuronpedia

    INDEX
    Explanations

    technical language

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     电
    0.64
     smokes
    0.61
    脳
    0.61
     static
    0.59
     從
    0.59
     vậy
    0.58
     株式会社
    0.58
     forge
    0.57
    静态
    0.56
     disintegrated
    0.56
    POSITIVE LOGITS
    names
    0.68
    file
    0.64
    sampling
    0.63
    icks
    0.60
    appropri
    0.60
     bayan
    0.60
    rows
    0.59
    secrets
    0.59
    shan
    0.58
     pakk
    0.58
    Act Density 0.000%

    No Known Activations