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

    Neuronpedia

    INDEX
    Explanations

    visually display SR elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    xssf
    0.43
    ępow
    0.41
    침
    0.41
    大战
    0.40
    preprocessing
    0.40
     dormitorio
    0.40
     অফিসে
    0.40
    стый
    0.40
     Poir
    0.40
    多多
    0.39
    POSITIVE LOGITS
     SR
    0.57
     visually
    0.55
     sr
    0.47
     Load
    0.47
    SR
    0.45
     LOAD
    0.44
    Loads
    0.44
     loads
    0.43
    visually
    0.43
    sr
    0.42
    Act Density 0.005%

    No Known Activations