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

    Neuronpedia

    INDEX
    Explanations

    ar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    spNet
    -0.08
     mentally
    -0.07
     Latvia
    -0.07
    _BANK
    -0.07
     neutron
    -0.07
     Represents
    -0.06
     elves
    -0.06
    打交
    -0.06
     champion
    -0.06
    ｜
    -0.06
    POSITIVE LOGITS
    -face
    0.06
    骗局
    0.06
    信托
    0.06
    ????
    0.06
    멀
    0.06
    สโม
    0.06
     Packages
    0.06
    供应
    0.06
    时刻
    0.06
    さら
    0.06
    Act Density 0.001%

    No Known Activations