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

    Neuronpedia

    INDEX
    Explanations

    Border Wait Times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     splice
    0.47
     పరి
    0.39
     NSDictionary
    0.39
     spliced
    0.38
     scenario
    0.38
     dilemma
    0.37
    헬
    0.37
    Switcher
    0.37
     CrL
    0.37
     величи
    0.37
    POSITIVE LOGITS
    reich
    0.44
    pleted
    0.39
    बाई
    0.38
     سنو
    0.37
     aumentando
    0.36
     Anywhere
    0.35
    úl
    0.34
    cao
    0.34
    patterns
    0.34
     હતી
    0.33
    Act Density 0.002%

    No Known Activations