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

    Neuronpedia

    INDEX
    Explanations

    in, of, for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    assistance
    0.49
    ChessBot
    0.45
     کاسینو
    0.45
     سپورټ
    0.43
    0.43
     упраж
    0.42
    stantially
    0.42
     січня
    0.42
     وړیا
    0.42
    ו
    0.42
    POSITIVE LOGITS
     pairs
    0.52
     decreases
    0.51
     hinges
    0.50
    م
    0.50
     electrolytes
    0.49
    ytes
    0.48
     switches
    0.48
     detergents
    0.47
     decreased
    0.46
     collected
    0.46
    Act Density 0.006%

    No Known Activations