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

    Neuronpedia

    INDEX
    Explanations

    expanding modern code details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ata
    0.37
    osas
    0.37
    允
    0.37
     irons
    0.36
     smartest
    0.36
     Monarch
    0.36
    örü
    0.36
     Grandpa
    0.36
    varphi
    0.35
     formul
    0.35
    POSITIVE LOGITS
     имуще
    0.47
     иногда
    0.39
    벧
    0.39
    这一点
    0.39
     denying
    0.38
     BUDGET
    0.37
    Budget
    0.36
    හු
    0.36
     budgets
    0.36
    在庫
    0.36
    Act Density 0.001%

    No Known Activations