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

    Neuronpedia

    INDEX
    Explanations

    technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    阿
    -0.07
    unded
    -0.07
    _input
    -0.07
    NG
    -0.06
    .metro
    -0.06
    瑞
    -0.06
    एम
    -0.06
    resource
    -0.06
    _section
    -0.06
     Domestic
    -0.06
    POSITIVE LOGITS
     verschill
    0.07
    (employee
    0.07
     çocu
    0.07
     Cele
    0.06
     Hay
    0.06
    であり
    0.06
    (len
    0.06
     Федера
    0.06
     stringWithFormat
    0.06
      
    0.06
    Act Density 1.763%

    No Known Activations