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

    Neuronpedia

    INDEX
    Explanations

    win-loss records

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    রোধ
    0.45
     ቀን
    0.40
     xlabel
    0.39
    𝚟
    0.39
    顺序
    0.38
    ⏱
    0.38
     scenario
    0.37
     চার্জ
    0.37
    鴳
    0.37
     уроке
    0.37
    POSITIVE LOGITS
    いております
    0.43
     Cer
    0.40
     Medical
    0.39
     Meet
    0.39
     Medi
    0.39
    The
    0.38
     pleno
    0.38
     Coon
    0.38
    malar
    0.38
     Fail
    0.38
    Act Density 0.003%

    No Known Activations