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

    Neuronpedia

    INDEX
    Explanations

    disorders

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    yb
    -0.07
     Rück
    -0.07
    hips
    -0.07
    ете
    -0.07
    嶂
    -0.07
    匆
    -0.06
    steel
    -0.06
     נית
    -0.06
    .OneToOne
    -0.06
    អ
    -0.06
    POSITIVE LOGITS
     disorders
    0.10
    Explorer
    0.08
     disorder
    0.08
    .comboBox
    0.08
     Disorders
    0.08
     ZIP
    0.07
     director
    0.07
    SpinBox
    0.07
     decoder
    0.07
     regularization
    0.07
    Act Density 0.008%

    No Known Activations