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

    Neuronpedia

    INDEX
    Explanations

    performance metrics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     %=
    -0.07
    adoras
    -0.07
    Observ
    -0.06
    급
    -0.06
     triangle
    -0.06
    +'&
    -0.06
    iscard
    -0.06
    .getSeconds
    -0.06
    getWindow
    -0.06
    ưới
    -0.06
    POSITIVE LOGITS
     tahmin
    0.07
     прим
    0.07
    amin
    0.07
     possessing
    0.07
     영화
    0.07
    ΕΡ
    0.06
     FR
    0.06
     pharm
    0.06
    438
    0.06
    oteca
    0.06
    Act Density 0.091%

    No Known Activations