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

    Neuronpedia

    INDEX
    Explanations

    ORDER

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .vocab
    -0.07
    绦
    -0.07
     vv
    -0.07
    urope
    -0.07
     every
    -0.07
    🍣
    -0.06
     wow
    -0.06
    ទ
    -0.06
    دن
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    (patient
    0.07
    חיפ
    0.07
    刑警
    0.07
    럐
    0.07
     pertinent
    0.07
    第二次
    0.06
     ("-
    0.06
     poignant
    0.06
    adier
    0.06
    疏散
    0.06
    Act Density 0.001%

    No Known Activations