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

    Neuronpedia

    INDEX
    Explanations

    technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    пр
    -0.07
    nore
    -0.06
     Horn
    -0.06
     Spatial
    -0.06
     disobed
    -0.06
     {?
    -0.06
     men
    -0.06
    με
    -0.06
     storms
    -0.06
     sorting
    -0.06
    POSITIVE LOGITS
    นคร
    0.07
    �
    0.07
    新
    0.07
     BO
    0.07
     vX
    0.06
    Partner
    0.06
    คร
    0.06
     Weiter
    0.06
     حاصل
    0.06
     每
    0.06
    Act Density 0.000%

    No Known Activations