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

    Neuronpedia

    INDEX
    Explanations

    Map

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nist
    -0.07
    叟
    -0.07
    .Serial
    -0.07
    eğe
    -0.07
    SED
    -0.07
    ışı
    -0.07
    忿
    -0.07
     youngsters
    -0.07
    dent
    -0.07
    Router
    -0.06
    POSITIVE LOGITS
    >:</
    0.07
    叮嘱
    0.07
    opl
    0.07
     bởi
    0.07
     المدينة
    0.06
     посколь
    0.06
     '↵↵
    0.06
    煲
    0.06
    .lb
    0.06
    ⌊
    0.06
    Act Density 0.001%

    No Known Activations