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

    Neuronpedia

    INDEX
    Explanations

    software configuration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .reader
    -0.07
     david
    -0.07
     которые
    -0.07
    Justice
    -0.07
     несколько
    -0.07
    ####↵
    -0.06
    「你
    -0.06
    
    -0.06
     أغسطس
    -0.06
    #######↵
    -0.06
    POSITIVE LOGITS
     walkthrough
    0.07
     government
    0.06
     ma
    0.06
    ษ
    0.06
    .getFloat
    0.06
     Beet
    0.06
     Sanity
    0.06
     přím
    0.06
    ูน
    0.06
    _typeDefinition
    0.06
    Act Density 0.103%

    No Known Activations