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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /export
    -0.09
    但我
    -0.08
     diligence
    -0.07
     dearly
    -0.07
    老龄化
    -0.07
    /list
    -0.07
     reflexivity
    -0.07
     MMA
    -0.07
     dönem
    -0.07
     Pension
    -0.07
    POSITIVE LOGITS
    щи
    0.07
     lateinit
    0.07
    INS
    0.06
    灶
    0.06
    	User
    0.06
    CK
    0.06
    won
    0.06
     straps
    0.06
    öm
    0.06
     //!↵
    0.06
    Act Density 0.020%

    No Known Activations