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
    oping
    -0.07
    (camera
    -0.07
     VT
    -0.07
     peso
    -0.07
    .iterator
    -0.07
    Bookmark
    -0.06
    賢
    -0.06
    Beyond
    -0.06
     écrit
    -0.06
     FTP
    -0.06
    POSITIVE LOGITS
    _student
    0.07
     Kah
    0.06
    workers
    0.06
    訴
    0.06
    련
    0.06
    flammatory
    0.06
     mocked
    0.06
     sodium
    0.06
     profiler
    0.06
    ایج
    0.06
    Act Density 0.004%

    No Known Activations