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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Circular
    -0.06
     mega
    -0.06
     reserva
    -0.06
     bleiben
    -0.06
     sito
    -0.06
    tractive
    -0.06
    -0.06
     charities
    -0.06
     việc
    -0.06
    独立
    -0.06
    POSITIVE LOGITS
    andel
    0.06
     encour
    0.06
     Enhanced
    0.06
    onden
    0.06
     ess
    0.06
    _lng
    0.06
     hy
    0.06
     guides
    0.06
     Lös
    0.06
     não
    0.06
    Act Density 0.002%

    No Known Activations