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

    Neuronpedia

    INDEX
    Explanations

    us

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    𫄧
    -0.07
    ../
    -0.06
     الو
    -0.06
     Servlet
    -0.06
    諸
    -0.06
     CONTRIBUT
    -0.06
    readcrumbs
    -0.06
    👝
    -0.06
     스스
    -0.06
    POSITIVE LOGITS
    副市长
    0.08
     למעשה
    0.08
     adhesive
    0.08
    发展
    0.08
     đặc
    0.07
     mic
    0.07
     ache
    0.07
     fantastic
    0.07
     CJ
    0.07
     galaxies
    0.07
    Act Density 0.224%

    No Known Activations