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

    Neuronpedia

    INDEX
    Explanations

    initial load

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    த்தின
    0.70
    थुरा
    0.68
    വി
    0.67
     marriages
    0.66
     গরীব
    0.66
     kamp
    0.65
    鳩
    0.63
    issam
    0.62
    iforme
    0.62
    pathTemplates
    0.62
    POSITIVE LOGITS
     load
    5.39
     Load
    5.05
    Load
    4.99
     loading
    4.95
    load
    4.91
     Loading
    4.63
     loads
    4.60
     loaded
    4.49
    Loading
    4.39
     LOAD
    4.32
    Act Density 0.608%

    No Known Activations