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
     exhilar
    -0.06
    stru
    -0.06
     Guth
    -0.06
     dashboard
    -0.06
     Dortmund
    -0.06
    因此
    -0.06
     planta
    -0.06
     AMC
    -0.05
     Bangkok
    -0.05
    زان
    -0.05
    POSITIVE LOGITS
     \(
    0.09
    \(
    0.08
    icy
    0.07
    門
    0.07
    -dom
    0.07
     recycled
    0.07
    >\<^
    0.07
    .cloudflare
    0.07
    ctica
    0.06
     auth
    0.06
    Act Density 0.020%

    No Known Activations