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

    Neuronpedia

    INDEX
    Explanations

    randomized controlled trials

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gos
    -0.08
    افية
    -0.08
     destination
    -0.07
    引越し
    -0.07
    avs
    -0.07
    инфекци
    -0.07
    請您提供
    -0.07
    Leod
    -0.07
     참여
    -0.06
    阒
    -0.06
    POSITIVE LOGITS
    ("&
    0.08
     adjustable
    0.07
     durable
    0.07
     EFF
    0.07
    否
    0.07
     flotation
    0.07
     zab
    0.06
     merc
    0.06
     dated
    0.06
    .RowCount
    0.06
    Act Density 0.031%

    No Known Activations