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

    Neuronpedia

    INDEX
    Explanations

    connecting phone by pin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ultimate
    0.43
    appList
    0.41
     oficialmente
    0.39
     quiet
    0.39
     loudest
    0.38
     endgame
    0.38
    केशन
    0.38
     beautiful
    0.38
    ော
    0.38
    Quiet
    0.37
    POSITIVE LOGITS
    ()'
    0.40
    usian
    0.40
    oxides
    0.39
    몄
    0.38
     humus
    0.37
    fur
    0.36
    0.36
    рма
    0.35
    找到了
    0.35
    发现了
    0.35
    Act Density 0.000%

    No Known Activations