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

    Neuronpedia

    INDEX
    Explanations

    Navigate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     followers
    -0.07
     stripped
    -0.07
     katkı
    -0.07
     proves
    -0.07
    残
    -0.07
     लग
    -0.07
    .С
    -0.06
     prestigious
    -0.06
     �
    -0.06
     stop
    -0.06
    POSITIVE LOGITS
    (sn
    0.07
    navigator
    0.06
     MethodInvocation
    0.06
     mới
    0.06
    .getAttribute
    0.06
    arth
    0.06
     Terra
    0.06
    877
    0.06
    process
    0.06
     domin
    0.06
    Act Density 0.013%

    No Known Activations