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

    Neuronpedia

    INDEX
    Explanations

    Software development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dynamic
    -0.07
     Tottenham
    -0.07
     m�
    -0.07
     você
    -0.07
    yah
    -0.07
     факт
    -0.07
    Tyler
    -0.06
     repent
    -0.06
     تلفن
    -0.06
    priority
    -0.06
    POSITIVE LOGITS
     covered
    0.07
    ),(
    0.07
     }),
    0.06
     throws
    0.06
    的是
    0.06
    103
    0.06
     cover
    0.06
     alleviate
    0.06
    berries
    0.05
    ρα
    0.05
    Act Density 0.040%

    No Known Activations