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

    Neuronpedia

    INDEX
    Explanations

    numbers and sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.54
    سي
    0.53
    нути
    0.52
    ات
    0.51
     questo
    0.50
    幅度
    0.50
    하고
    0.50
    거
    0.49
     habit
    0.48
     dose
    0.48
    POSITIVE LOGITS
    xes
    0.54
     assumptive
    0.52
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.50
     оформления
    0.50
     GTEST
    0.50
     Asalamualaikum
    0.49
     domaines
    0.49
    მასრულ
    0.49
     Tất
    0.49
    dns
    0.48
    Act Density 0.199%

    No Known Activations