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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interchangeable
    -0.08
     atawa
    -0.08
     utawa
    -0.08
     الخار
    -0.08
     atanapi
    -0.07
     некалькі
    -0.07
     birkaç
    -0.07
     hesitate
    -0.07
    Frequently
    -0.07
     pard
    -0.07
    POSITIVE LOGITS
    符合
    0.10
    fulfilled
    0.08
     mechanism
    0.08
     demonstrates
    0.08
    验证
    0.08
     satisfaction
    0.08
     satisfied
    0.08
    满足
    0.08
     agreeable
    0.08
    验
    0.08
    Act Density 0.114%

    No Known Activations