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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     maturity
    -0.06
    貨
    -0.06
    čer
    -0.06
     десяти
    -0.06
     plag
    -0.06
    	cell
    -0.06
    usahaan
    -0.06
    ��
    -0.06
     แพ
    -0.06
     convent
    -0.06
    POSITIVE LOGITS
     Transactions
    0.07
    ,
↵
    0.07
    Messaging
    0.06
     immobil
    0.06
    ascript
    0.06
     rehabilit
    0.06
    .random
    0.06
    rowing
    0.06
    Anchor
    0.06
     modules
    0.06
    Act Density 0.003%

    No Known Activations