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

    Neuronpedia

    INDEX
    Explanations

    Sit comfortably, hours grinding, panicked search

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pretensions
    0.51
     motifs
    0.47
     anivers
    0.46
     spese
    0.45
     HttpServer
    0.45
     Nus
    0.45
     nascost
    0.45
     risiko
    0.44
     testimonio
    0.44
     raisons
    0.44
    POSITIVE LOGITS
    In
    0.47
    В
    0.47
    Rough
    0.47
    Ok
    0.46
    Azer
    0.46
    تر
    0.46
    Investment
    0.46
    يد
    0.45
    Desert
    0.45
    Rolling
    0.44
    Act Density 0.002%

    No Known Activations