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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    фи
    -0.07
     improve
    -0.07
    (FALSE
    -0.07
    ені
    -0.07
     디자인
    -0.06
     Nelson
    -0.06
     nemoc
    -0.06
     consulting
    -0.06
     역사
    -0.06
    ervative
    -0.06
    POSITIVE LOGITS
     外部
    0.06
    ایند
    0.06
    可是
    0.06
     그렇
    0.06
     maybe
    0.06
    ыв
    0.06
    SESSION
    0.06
    如
    0.06
    ieur
    0.06
    .IP
    0.06
    Act Density 0.053%

    No Known Activations