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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     وبين
    -0.07
     getConnection
    -0.07
    骑兵
    -0.06
     improbable
    -0.06
    荣幸
    -0.06
     비교
    -0.06
    (observer
    -0.06
     Infer
    -0.06
     gridColumn
    -0.06
    .onClick
    -0.06
    POSITIVE LOGITS
    大幅
    0.07
     chasing
    0.07
    Core
    0.07
     grocery
    0.07
     Scene
    0.07
    습
    0.07
    Actions
    0.07
     duyệt
    0.06
     scene
    0.06
    OU
    0.06
    Act Density 0.011%

    No Known Activations