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

    Neuronpedia

    INDEX
    Explanations

    IO

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𝑡
    -0.07
    言
    -0.07
    电路
    -0.07
     terme
    -0.07
     dàng
    -0.07
     resourceName
    -0.06
    :e
    -0.06
    gement
    -0.06
    😠
    -0.06
     Garner
    -0.06
    POSITIVE LOGITS
     저
    0.08
     OH
    0.07
    庵
    0.07
     thinkers
    0.07
     Newest
    0.07
     Surv
    0.07
    ѭ
    0.07
     PERF
    0.07
    .AP
    0.07
    far
    0.07
    Act Density 0.001%

    No Known Activations