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

    Neuronpedia

    INDEX
    Explanations

    treatment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     treatment
    -1.82
     Treatment
    -1.59
    treatment
    -1.58
    Treatment
    -1.57
     treat
    -1.52
     treatments
    -1.46
     treated
    -1.45
     Treat
    -1.44
     TREATMENT
    -1.43
     treating
    -1.41
    POSITIVE LOGITS
     FetchType
    1.03
     الحره
    0.95
    +#+#
    0.93
    gonic
    0.93
    WebVitals
    0.92
    IonicModule
    0.90
     للمعارف
    0.90
    UpInside
    0.89
    MemoryWarning
    0.89
    aarrggbb
    0.89
    Act Density 1.545%

    No Known Activations