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

    Neuronpedia

    INDEX
    Explanations

    user interface and visuals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !!
    0.42
    Parent
    0.39
    Base
    0.37
    است
    0.37
    Left
    0.37
    Insert
    0.36
    Car
    0.36
    obj
    0.36
    Availability
    0.36
    Powerful
    0.35
    POSITIVE LOGITS
     aesthetically
    0.82
     aesthetics
    0.74
     aesthetic
    0.73
     visuals
    0.73
     visualisation
    0.73
     visually
    0.72
     esth
    0.72
     visual
    0.70
     visualization
    0.70
     graphical
    0.70
    Act Density 0.489%

    No Known Activations