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

    Neuronpedia

    INDEX
    Explanations

    you see

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    다
    0.80
     વખતે
    0.79
    ษฐ
    0.77
     militare
    0.74
    สอน
    0.73
    추
    0.73
    στηκε
    0.73
    ቹን
    0.73
    zinha
    0.73
     calcula
    0.73
    POSITIVE LOGITS
    bygg
    0.77
    类
    0.74
     syg
    0.70
     DEP
    0.69
     Attacks
    0.67
     overwhelming
    0.66
     Shabd
    0.65
    实体
    0.65
     Marshal
    0.64
     THF
    0.63
    Act Density 0.000%

    No Known Activations