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

    Neuronpedia

    INDEX
    Explanations

    leader

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /cupertino
    -0.07
    rench
    -0.07
     cul
    -0.07
    Compatible
    -0.07
    כבד
    -0.07
     Meyer
    -0.07
    Render
    -0.07
    谆
    -0.06
    widgets
    -0.06
    .read
    -0.06
    POSITIVE LOGITS
    饮用
    0.07
    的压力
    0.07
     inserted
    0.07
    _Profile
    0.06
    LAG
    0.06
    ировка
    0.06
    积极作用
    0.06
    좉
    0.06
    ались
    0.06
    茳
    0.06
    Act Density 0.021%

    No Known Activations