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

    Neuronpedia

    INDEX
    Explanations

    add

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Cho
    -0.07
    _foot
    -0.07
    ادة
    -0.07
     Completion
    -0.07
    🐣
    -0.07
     GLUT
    -0.07
     comme
    -0.07
    ée
    -0.07
     Dropdown
    -0.06
     começou
    -0.06
    POSITIVE LOGITS
     enforced
    0.07
    侮
    0.07
    风气
    0.07
     Nas
    0.07
    之前
    0.07
    PRS
    0.07
    НА
    0.07
    VK
    0.06
    樱
    0.06
     hormones
    0.06
    Act Density 0.013%

    No Known Activations