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

    Neuronpedia

    INDEX
    Explanations

    economics and products

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unsafe
    -0.06
    _iterations
    -0.06
    icum
    -0.06
    IPH
    -0.06
    .Thread
    -0.06
     chaotic
    -0.06
    aci
    -0.06
     campus
    -0.06
     собой
    -0.06
     Registration
    -0.06
    POSITIVE LOGITS
    =<
    0.07
     witty
    0.07
    !");↵
    0.07
     TEntity
    0.06
    ={<
    0.06
    غ
    0.06
     silky
    0.06
    !!}</
    0.06
    并不
    0.06
    foy
    0.06
    Act Density 0.279%

    No Known Activations