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

    Neuronpedia

    INDEX
    Explanations

    updated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mach
    -0.06
    uity
    -0.06
    893
    -0.06
    ��
    -0.06
    SAVE
    -0.06
    Province
    -0.06
    achment
    -0.06
    ThreadPool
    -0.06
    (dr
    -0.06
    versation
    -0.06
    POSITIVE LOGITS
    Silver
    0.07
     culprit
    0.07
     aspect
    0.06
    Ngh
    0.06
     انجمن
    0.06
     },{↵
    0.06
    .assertEqual
    0.06
     second
    0.06
    gambar
    0.06
     work
    0.06
    Act Density 0.023%

    No Known Activations