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

    Neuronpedia

    INDEX
    Explanations

    exactly

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Modules
    -0.07
     Arte
    -0.07
     thác
    -0.07
    (TestCase
    -0.07
     organis
    -0.06
     MVC
    -0.06
     FileNotFoundError
    -0.06
    .max
    -0.06
     pathways
    -0.06
     tuples
    -0.06
    POSITIVE LOGITS
    ขณะท
    0.06
    odom
    0.06
     바로
    0.06
     Mustafa
    0.06
     Adam
    0.06
    prec
    0.06
     intox
    0.06
    ีพ
    0.06
    xd
    0.06
    enh
    0.06
    Act Density 0.008%

    No Known Activations