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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    廳
    -0.07
    Saturday
    -0.07
    πο
    -0.06
    .),
    -0.06
     consequences
    -0.06
     спор
    -0.06
    ة
    -0.06
     hrá
    -0.06
    ่ว
    -0.06
    indrical
    -0.06
    POSITIVE LOGITS
    	select
    0.07
    emails
    0.06
    302
    0.06
    (constants
    0.06
     approaches
    0.06
     numberWith
    0.06
    념
    0.06
     patches
    0.06
    AGE
    0.06
     giống
    0.06
    Act Density 0.000%

    No Known Activations