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

    Neuronpedia

    INDEX
    Explanations

    showing or showcasing visual content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    constants
    0.72
    يال
    0.71
    ède
    0.70
     ይችላል
    0.67
    ütün
    0.66
     reckoned
    0.66
    cidas
    0.66
    venty
    0.65
    فكير
    0.65
    atiable
    0.64
    POSITIVE LOGITS
     smiling
    1.63
     cityscape
    1.44
     closeup
    1.26
     Smiling
    1.22
     zoomed
    1.21
     showcasing
    1.21
     beautiful
    1.21
     scenery
    1.20
     lush
    1.20
     gorgeous
    1.19
    Act Density 0.217%

    No Known Activations