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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ン
    -0.07
     moderated
    -0.07
    ToRemove
    -0.06
    ph
    -0.06
    Servlet
    -0.06
    trinsic
    -0.06
    ありません
    -0.06
     thấy
    -0.06
     gereken
    -0.06
     raison
    -0.06
    POSITIVE LOGITS
    得到
    0.07
    hashed
    0.06
    _radio
    0.06
     pix
    0.06
    difficulty
    0.06
    ická
    0.06
    纪
    0.06
    Ont
    0.06
    (rr
    0.06
     recognizing
    0.06
    Act Density 0.004%

    No Known Activations