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

    Neuronpedia

    INDEX
    Explanations

    abandoned

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     together
    -0.06
    隙
    -0.06
    과
    -0.06
    𫟦
    -0.06
    畬
    -0.06
    池
    -0.06
    শ
    -0.06
    ﺫ
    -0.06
    夬
    -0.06
    ч
    -0.06
    POSITIVE LOGITS
    亲眼
    0.08
    💒
    0.08
    /test
    0.08
    €�
    0.08
     마음
    0.07
    不动产
    0.07
     linha
    0.07
    Kn
    0.07
     Marketplace
    0.07
    Photo
    0.07
    Act Density 0.031%

    No Known Activations