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

    Neuronpedia

    INDEX
    Explanations

    rotor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    klä
    -0.07
     studi
    -0.07
     hindi
    -0.07
               
    -0.06
     gameState
    -0.06
    опис
    -0.06
     Martinez
    -0.06
    Done
    -0.06
    edl
    -0.06
    DBG
    -0.06
    POSITIVE LOGITS
     rotor
    0.09
     raison
    0.08
    ери
    0.07
     рок
    0.06
    nero
    0.06
    實
    0.06
    .ToTable
    0.06
    lider
    0.06
    eru
    0.06
    787
    0.06
    Act Density 0.002%

    No Known Activations