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

    Neuronpedia

    INDEX
    Explanations

    ROS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    effective
    -0.07
    支援
    -0.07
     inventions
    -0.07
    唿
    -0.07
     heuristic
    -0.07
     Indian
    -0.07
    回馈
    -0.07
    安抚
    -0.07
    Sections
    -0.07
     toughest
    -0.07
    POSITIVE LOGITS
    实木
    0.08
    ⁺
    0.08
    renders
    0.07
     dealloc
    0.07
    𝔷
    0.07
    SpinBox
    0.07
    峄
    0.07
    ,pos
    0.07
    ömür
    0.06
    眦
    0.06
    Act Density 0.001%

    No Known Activations