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

    Neuronpedia

    INDEX
    Explanations

    everyday products, manufacturing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     towers
    -0.07
    =h
    -0.07
    =str
    -0.06
    )new
    -0.06
     Pool
    -0.06
    Style
    -0.06
    =B
    -0.06
     يم
    -0.06
    -town
    -0.06
    elts
    -0.06
    POSITIVE LOGITS
     Simply
    0.07
    风险
    0.07
    .ViewModels
    0.06
    редит
    0.06
    (ag
    0.06
     sequel
    0.06
    ΑΔ
    0.06
    OrderId
    0.06
    .Ch
    0.06
    .power
    0.06
    Act Density 0.057%

    No Known Activations