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

    Neuronpedia

    INDEX
    Explanations

    text from research papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ']},↵
    -0.07
     aloud
    -0.07
     обуч
    -0.07
     smiled
    -0.07
    plaintext
    -0.07
    quare
    -0.07
    toBe
    -0.07
     منهم
    -0.07
    toArray
    -0.07
     apr
    -0.07
    POSITIVE LOGITS
     Exchange
    0.07
     Writers
    0.07
    _Map
    0.07
    .Department
    0.07
    会展中心
    0.06
    Seat
    0.06
     Nữ
    0.06
    วล
    0.06
     Clash
    0.06
    Partition
    0.06
    Act Density 0.000%

    No Known Activations