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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jeep
    -0.06
    微软雅黑
    -0.06
     moh
    -0.06
    =q
    -0.06
    raně
    -0.06
     traction
    -0.06
    کتر
    -0.06
     fraction
    -0.06
    :ss
    -0.06
     mesh
    -0.06
    POSITIVE LOGITS
     whispered
    0.07
     üzerine
    0.06
    无法
    0.06
     annoying
    0.06
     código
    0.06
     annoy
    0.06
     ihtiyaç
    0.06
     gli
    0.06
     вку
    0.06
     genie
    0.06
    Act Density 0.009%

    No Known Activations