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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BorderColor
    -0.08
    moz
    -0.07
    TextStyle
    -0.07
     //////////////////////////////////////////////////////////////////////
    -0.07
    Product
    -0.07
    _ot
    -0.07
    ‟
    -0.07
    培
    -0.07
    ropol
    -0.06
    렉
    -0.06
    POSITIVE LOGITS
    用户的
    0.07
     Lily
    0.07
    	A
    0.07
     ראיתי
    0.06
    DAT
    0.06
     coaster
    0.06
    .Email
    0.06
     cartridge
    0.06
    忠诚
    0.06
    favor
    0.06
    Act Density 0.010%

    No Known Activations