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

    Neuronpedia

    INDEX
    Explanations

    Separators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _room
    -0.07
     Grain
    -0.07
    管理水平
    -0.07
     disjoint
    -0.07
     denomination
    -0.07
     velvet
    -0.07
     presidential
    -0.07
     DISPATCH
    -0.07
     уни
    -0.07
    /bus
    -0.07
    POSITIVE LOGITS
    拿到
    0.07
    ги
    0.07
    齡
    0.07
    릭
    0.07
    .borrow
    0.07
     áo
    0.07
    izacao
    0.07
    _correct
    0.07
    .topic
    0.07
    ≃
    0.07
    Act Density 0.016%

    No Known Activations