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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     toString
    -0.06
    овари
    -0.06
    ---
↵
    -0.06
    Ctr
    -0.06
    .Success
    -0.06
     Mexico
    -0.06
    Supply
    -0.06
     Tage
    -0.06
    (api
    -0.06
    .Max
    -0.06
    POSITIVE LOGITS
    ecom
    0.06
     Pand
    0.06
     Senators
    0.06
     caval
    0.06
     shed
    0.06
    acom
    0.06
    ikit
    0.06
     Sv
    0.06
    ротив
    0.06
    _dirty
    0.06
    Act Density 0.039%

    No Known Activations