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

    Neuronpedia

    INDEX
    Explanations

    code and transcripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     된다
    -0.07
     Polar
    -0.07
    ToolTip
    -0.07
     aan
    -0.06
     частина
    -0.06
    ListAdapter
    -0.06
     gated
    -0.06
     �
    -0.06
     Αρχ
    -0.06
    itemid
    -0.06
    POSITIVE LOGITS
     FK
    0.08
    )*/↵
    0.07
    PT
    0.07
     JV
    0.06
     Participant
    0.06
    pt
    0.06
    .solve
    0.06
    itech
    0.06
    pdata
    0.06
    CC
    0.06
    Act Density 0.013%

    No Known Activations