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

    Neuronpedia

    INDEX
    Explanations

    review

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dw
    -0.07
     lt
    -0.07
     sen
    -0.07
    .depart
    -0.07
     nerv
    -0.07
     KY
    -0.07
    续约
    -0.07
     TU
    -0.07
     Throwable
    -0.06
     mau
    -0.06
    POSITIVE LOGITS
    疫情防控
    0.07
    .effects
    0.07
    不会
    0.07
    cost
    0.07
     Percentage
    0.07
    ﻗ
    0.07
    ORG
    0.07
    (accounts
    0.07
    _boost
    0.07
     splitter
    0.07
    Act Density 0.009%

    No Known Activations