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

    Neuronpedia

    INDEX
    Explanations

    organized plans

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ξ
    -0.07
     advisable
    -0.07
    annotation
    -0.07
    根本
    -0.06
    -leaning
    -0.06
    怎么
    -0.06
    ารถ
    -0.06
     jejichž
    -0.06
     варі
    -0.06
    apt
    -0.06
    POSITIVE LOGITS
     		↵
    0.06
     büyük
    0.06
     cedar
    0.06
     ces
    0.06
     tông
    0.06
     witnessed
    0.06
    LPARAM
    0.06
     چشم
    0.06
    estation
    0.06
    'aut
    0.06
    Act Density 0.099%

    No Known Activations