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

    Neuronpedia

    INDEX
    Explanations

    adverbial phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    गौरतलब
    0.54
    ジョ
    0.50
    诋
    0.50
     damal
    0.50
    валися
    0.49
    詆
    0.48
    結局
    0.48
     सिंपली
    0.48
     بسبب
    0.46
     kvůli
    0.46
    POSITIVE LOGITS
     outcrops
    0.49
     aspires
    0.49
     internships
    0.49
     develops
    0.49
     periodically
    0.48
     nascent
    0.47
     on
    0.47
     encounters
    0.47
     auf
    0.46
     activities
    0.46
    Act Density 0.010%

    No Known Activations