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

    Neuronpedia

    INDEX
    Explanations

    lists of requirements or reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    りが
    0.44
    ,’’
    0.43
    ){}^
    0.43
    。",
    0.43
    ]^
    0.40
    斯的
    0.39
    点が
    0.38
    ெடு
    0.38
    公斤
    0.38
     fenomeni
    0.38
    POSITIVE LOGITS
     whims
    0.50
     واع
    0.49
    לח
    0.46
     estable
    0.46
     florals
    0.46
     properties
    0.46
     especificar
    0.46
     exuberant
    0.45
    ల
    0.45
    나
    0.45
    Act Density 0.001%

    No Known Activations