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

    Neuronpedia

    INDEX
    Explanations

    volume data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    0.48
     plot
    0.46
     Matlab
    0.45
     relieving
    0.45
     Scene
    0.44
     Leveraging
    0.44
    I
    0.44
     step
    0.44
     Maine
    0.43
     Step
    0.42
    POSITIVE LOGITS
     alguns
    0.60
     alcuni
    0.50
     algunos
    0.49
    માં
    0.49
     asesor
    0.49
    වින්
    0.48
    SleepHours
    0.48
     naciones
    0.48
    DEPENDENCIA
    0.48
    ∫
    0.47
    Act Density 0.001%

    No Known Activations