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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
    رق
    -0.06
     murdered
    -0.06
    盒
    -0.06
    РА
    -0.06
     Algebra
    -0.06
     asshole
    -0.06
     ruh
    -0.06
    bill
    -0.06
     legs
    -0.06
    POSITIVE LOGITS
     VE
    0.07
    .
↵
    0.07
    lardan
    0.07
    .Strict
    0.07
     Hyp
    0.06
     Tata
    0.06
     بتن
    0.06
    ...↵↵↵↵
    0.06
     آنان
    0.06
     Φ
    0.06
    Act Density 0.038%

    No Known Activations