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

    Neuronpedia

    INDEX
    Explanations

    geometry and measurement

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     horns
    0.70
     மா
    0.69
     model
    0.69
     রক্তের
    0.68
     brushes
    0.65
     Model
    0.65
     शही
    0.65
     brush
    0.65
     appeal
    0.64
     gases
    0.64
    POSITIVE LOGITS
    Altitude
    0.87
     Altitude
    0.81
     bis
    0.80
    Bis
    0.79
     circun
    0.78
    altitude
    0.73
    Pron
    0.72
    Construction
    0.71
    Copy
    0.70
    Ẩ
    0.70
    Act Density 0.075%

    No Known Activations