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

    Neuronpedia

    INDEX
    Explanations

    Articles and adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    体现
    -0.07
    푀
    -0.07
    𬙂
    -0.07
     Ind
    -0.07
    .nn
    -0.07
     sangat
    -0.07
     ascend
    -0.07
    sup
    -0.06
     Ib
    -0.06
     ended
    -0.06
    POSITIVE LOGITS
    多功能
    0.08
     intolerance
    0.07
     pharmaceutical
    0.07
     █████
    0.07
    套装
    0.07
     shuttle
    0.07
     ®
    0.07
     fracking
    0.07
     numérique
    0.07
    稑
    0.07
    Act Density 0.085%

    No Known Activations