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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    מטופל
    -0.07
    瑬
    -0.07
     VIN
    -0.07
    皛
    -0.07
    蛩
    -0.07
    哕
    -0.07
     väl
    -0.07
    爲
    -0.07
    쪼
    -0.07
    ถน
    -0.07
    POSITIVE LOGITS
    (Get
    0.07
    叔叔
    0.07
     Tig
    0.07
     -----
    0.07
     피해
    0.07
    (math
    0.07
    (debug
    0.07
    如果不是
    0.07
     revised
    0.07
    (inner
    0.07
    Act Density 0.228%

    No Known Activations